How to use google/gemma-4-12B-it with Transformers:
# Load model directly from transformers import AutoProcessor, AutoModelForMultimodalLM processor = AutoProcessor.from_pretrained("google/gemma-4-12B-it") model = AutoModelForMultimodalLM.from_pretrained("google/gemma-4-12B-it", device_map="auto")
I understand that SAE (Sparse Autoencoders) is an important piece of work for model interpretability.I have also seen GemmaScope, which is applicable to gemma-2-9b.Does your team have any plans to release SAEs compatible with gemma-4-12b-it?
· Sign up or log in to comment
