© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 119305
    Prev
    Next
    INDEX
    Explanations

    actions associated with group dynamics and adventures involving young people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    names carved on trees

    np_acts-logits-general · gemini-2.5-flash-lite

    descriptions of people engaged in active, often recreational movement or travel, highlighting physical actions, motion, and group interaction.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FXMLLoader
    -0.33
     voorkomen
    -0.32
    événement
    -0.31
    WebElementEntity
    -0.29
     aspect
    -0.28
     Gardiner
    -0.28
     figure
    -0.28
    comuna
    -0.28
     event
    -0.27
     reserves
    -0.27
    POSITIVE LOGITS
    ValueStyle
    0.55
    twimg
    0.54
    abestanden
    0.54
     <<<<<<<<<<<<<<
    0.53
    +#+
    0.51
     ExecuteAsync
    0.51
    Bakgrunnsstoff
    0.51
     THEATRE
    0.50
    theatre
    0.50
    IsContent
    0.50
    Activations Density 0.062%

    No Known Activations