© 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. 44083
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistics related to market reports

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

    market research reports

    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
     estekak
    -0.55
    TemporalType
    -0.54
     newBuilder
    -0.52
    HomeAsUpEnabled
    -0.51
     שוליים
    -0.49
     beginnetje
    -0.48
    OGND
    -0.47
    urlpatterns
    -0.45
     мәкал
    -0.42
     ویکی‌پدیا
    -0.42
    POSITIVE LOGITS
     forecasts
    0.68
     consultancy
    0.68
     analysts
    0.68
     consulting
    0.63
     research
    0.63
     analyst
    0.62
     researcher
    0.58
     researchers
    0.58
    research
    0.58
     market
    0.56
    Activations Density 0.026%

    No Known Activations