© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 16k - L0 32+
    9. 26-GEMMASCOPE-MLP-16K-L0_32PLUS
    gemma-2-9b · 26-gemmascope-mlp-16k-l0_32plus
    Source from gemma-scope · MLP Out - 16k - L0 32+ · Layer 26
    Jump to Source/SAE
    Jump to Feature
    INDEX

    Configuration

    google/gemma-scope-9b-pt-mlp/layer_26/width_16k/average_l0_57
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.26.hook_mlp_out
    Hook Layer
    26
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu

    Search Explanations

    Browse

    Features in GEMMA-2-9B@26-gemmascope-mlp-16k-l0_32plus
    1. Hover over a feature on the left to preview its details.
    2. Click a feature to lock it and interact with it.