© 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. 75649
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals and their relationships or interactions

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

    family, mentors, partners

    np_acts-logits-general · gemini-2.5-flash-lite

    tokens that are person names or other person-related named-entity words (people, roles, and similar proper nouns).

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     opérés
    -0.40
    dAtA
    -0.40
     ур
    -0.37
    profil
    -0.36
     beginnetje
    -0.36
    تفصیلات
    -0.34
     Profiling
    -0.34
    клопе
    -0.34
     pair
    -0.34
    Profil
    -0.33
    POSITIVE LOGITS
    parsedMessage
    0.54
    StructEnd
    0.51
     تانيه
    0.51
    CheckBreak
    0.48
    DrawerToggle
    0.48
    HomeAsUpEnabled
    0.45
     sàng
    0.43
    OrBuilder
    0.41
     noastră
    0.40
    czych
    0.39
    Activations Density 0.257%

    No Known Activations