© 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. 9838
    Prev
    Next
    INDEX
    Explanations

    language related to inquiries or issues within a customer service context

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

    contact us or problems

    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
    GTCX
    -0.47
    MigrationBuilder
    -0.45
    rrggbb
    -0.36
    jspx
    -0.35
    EDEFAULT
    -0.34
    CreateTable
    -0.34
    èo
    -0.33
     endwhile
    -0.33
    ScopeManager
    -0.33
    andaag
    -0.33
    POSITIVE LOGITS
     feel
    0.68
    feel
    0.59
     Feel
    0.59
    Feel
    0.57
    contact
    0.56
     sensazione
    0.56
     please
    0.55
     contact
    0.54
    Contact
    0.54
     FEEL
    0.53
    Activations Density 0.001%

    No Known Activations