© 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. 31-GEMMASCOPE-RES-131K
    11. 66073
    Prev
    Next
    INDEX
    Explanations

    punctuation and formatting elements, indicating structured or technical language

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

    `user` after `<start_of_turn>`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagext
    -0.56
    InitVars
    -0.43
    rophes
    -0.43
    rungsseite
    -0.43
    CloseOperation
    -0.42
     HasFactory
    -0.40
    PrototypeOf
    -0.39
     aDecoder
    -0.37
    İY
    -0.37
    ércoles
    -0.36
    POSITIVE LOGITS
    どうなる
    0.49
     normais
    0.48
     Ganzen
    0.47
     ""));
    0.47
     normaux
    0.47
    )['
    0.46
    อื่น
    0.46
     ""))
    0.45
     čierna
    0.44
     conventional
    0.44
    Activations Density 0.000%

    No Known Activations