Abstract A recurrent neural network fitted to large electrophysiological datasets may help us understand the chain of cortical information transmission. In particular, successful network reconstruction methods should enable a model to predict the response to optogenetic perturbations. We test recurrent neural networks (RNNs) fitted to electrophysiological datasets on unseen optogenetic interventions, and measure that generic RNNs used predominantly in the field generalize poorly on these perturbations. Our alternative RNN model adds biologically informed inductive biases like structured connectivity of excitatory and inhibitory neurons and spiking neuron dynamics. We measure that some of the biological inductive biases can improve the model prediction under perturbation in a simulated dataset and a dataset recorded in mice in vivo. Furthermore, we show in simulations that gradients of the fitted RNN can predict the effect of micro-perturbations in the recorded circuits, and discuss potentials for measuring brain gradients or using gradient-targeted stimulation to bias an animal behavior.