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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K__L0-22
    6. 911
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fml
    -0.50
    zzleHttp
    -0.47
    liyor
    -0.47
     löyty
    -0.47
    phosa
    -0.44
    gatsby
    -0.44
     accue
    -0.44
     nélkül
    -0.43
     encima
    -0.43
     heller
    -0.43
    POSITIVE LOGITS
     ComVisible
    0.85
    ReusableCell
    0.76
    RenderAtEndOf
    0.66
    homonymie
    0.64
    StoreMessageInfo
    0.62
    GEBURTSDATUM
    0.61
    }';
    0.61
    MigrationBuilder
    0.59
    typeorm
    0.57
     fieldNum
    0.56
    Activations Density 0.087%

    No Known Activations