© 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. 31-GEMMASCOPE-RES-131K
    11. 21137
    Prev
    Next
    INDEX
    Explanations

    mentions of specific female names, particularly those involved in notable narratives

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

    people's names

    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
     totalidad
    -0.34
     pudieran
    -0.34
    Harrison
    -0.33
     avenir
    -0.32
     parent
    -0.31
     Otro
    -0.31
     compañía
    -0.30
    ykite
    -0.29
     creación
    -0.29
    ³/
    -0.29
    POSITIVE LOGITS
    NameInMap
    0.71
    SharedDtor
    0.66
    s
    0.63
    writeFieldEnd
    0.61
    PerformLayout
    0.61
    QMetaType
    0.60
    eliness
    0.60
     ErrIntOverflow
    0.59
    exitRule
    0.58
    lccc
    0.57
    Activations Density 0.016%

    No Known Activations