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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 107580
    Prev
    Next
    INDEX
    Explanations

    the repetition and emphasis of the character "一" (one) in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    `.`
    -0.51
    ActionMode
    -0.47
    <h3>
    -0.47
     actionTypes
    -0.46
    onBlur
    -0.46
     modem
    -0.42
    (=)
    -0.42
    ual
    -0.42
    GCM
    -0.41
    Mila
    -0.41
    POSITIVE LOGITS
    awtextra
    0.60
    heids
    0.60
    ptonshire
    0.56
     onPostExecute
    0.55
     disambiguazione
    0.52
     Că
    0.52
    bindet
    0.52
    QMetaType
    0.52
    BorderFactory
    0.52
    下一
    0.52
    Activations Density 0.005%

    No Known Activations