The dynamic interplay of inhibitory and excitatory neurons drives the cortical functional repertoire. In the mammalian neocortex, inhibitory neurons are diverse. They are characterized by a variety of cellular attributes that enable their specialized roles in regulating information processing. It is increasingly clear that the major subtype specification of inhibitory neurons is given by their molecular identity, defined by techniques such as gene expression profiling. However, the molecular class alone provides limited insight into the anatomical, physiological, and connectivity properties of inhibitory neurons. A key open question is how the diversity of inhibitory neurons is organized across cortical layers and how this organization shapes the architecture of cortical circuits. Here we assess variations in morphology, electrophysiology, and gene expression profiles across the entire depth of mouse visual cortex. These variations reveal depth-dependent gradients of morphoelectric properties, regardless of molecular identity. We find that the overall axonal and dendritic arborizations increase with depth, exhibiting similar degrees of diversity in each layer. A link between morphology, electrophysiology, and molecular identity can be defined with such gradients across layers. We then utilized millimeter-scale volumetric electron microscopy to investigate the connectivity patterns of inhibitory neurons across layers. In this case, not only does the morphology increase across layers, but also the number of input and output synapses. To assess the uniformity of this observation, we analyzed inhibitory neurons in mouse motor cortex and human middle temporal gyrus. In both species and cortical areas, the neuron size increases as a function of depth, independent of subtype. This correspondence among gradients of cellular attributes indicate a structural principle that organizes the diversity of inhibitory neurons. Thus, we find support for the hypothesis that inhibitory neurons shape their local environment to a large extent by adjusting their cellular attributes during the development of neural circuits.