© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Attention Out - 65k
    9. 15-GEMMASCOPE-ATT-65K
    gemma-2-2b · 15-gemmascope-att-65k
    Source from gemma-scope · Attention Out - 65k · Layer 15
    Jump to Source/SAE
    Jump to Feature
    INDEX

    Configuration

    google/gemma-scope-2b-pt-att/layer_15/width_65k/average_l0_90
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.15.attn.hook_z
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu

    Search Explanations

    Browse

    Features in GEMMA-2-2B@15-gemmascope-att-65k
    1. Hover over a feature on the left to preview its details.
    2. Click a feature to lock it and interact with it.