© 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 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. 9-GEMMASCOPE-RES-131K
    11. 29581
    Prev
    Next
    INDEX
    Explanations

    terms associated with legal and financial obligations

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

    restitution, embezzlement, impregnated, artichokes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     franquicia
    -0.48
    fromLTRB
    -0.46
     inalámbrica
    -0.45
     kolye
    -0.44
     Histórico
    -0.44
     fidélité
    -0.43
     richieste
    -0.43
     valentín
    -0.42
    clays
    -0.42
     maleta
    -0.42
    POSITIVE LOGITS
     Tunisia
    0.93
     Riviera
    0.78
     Brie
    0.75
    brie
    0.73
    setVerticalGroup
    0.70
     Arti
    0.68
    Tunisia
    0.68
     Judea
    0.65
     brie
    0.65
    Brie
    0.65
    Activations Density 0.007%

    No Known Activations