© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 9535
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns related to influence and legacy

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

    influence and impact

    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
    ="@+
    -0.38
     kebutuhan
    -0.33
    Needs
    -0.33
     بخ
    -0.31
     sécur
    -0.30
     Needs
    -0.30
     lät
    -0.30
    KommentareTeilen
    -0.29
     logistique
    -0.29
     Wants
    -0.29
    POSITIVE LOGITS
     influence
    1.99
    influence
    1.76
     impact
    1.73
    Influence
    1.73
     Influence
    1.72
     influential
    1.62
    influ
    1.56
     INFLUENCE
    1.55
     influences
    1.54
    影響
    1.54
    Activations Density 0.131%

    No Known Activations