© 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-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 635
    Prev
    Next
    INDEX
    Explanations

    financial data related to regional economic development and infrastructure projects

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

    references to economic metrics and highway designations

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

    doubt about specific facts or numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ivelany
    -0.85
     فريبيس
    -0.85
    Искәрмәләр
    -0.77
    KURZBESCHREIBUNG
    -0.77
    principalColumn
    -0.77
     שוליים
    -0.74
    IntoConstraints
    -0.72
    TypedDataSet
    -0.71
     ligiloj
    -0.70
    yntaxException
    -0.69
    POSITIVE LOGITS
     Preferred
    0.44
     وتسجيلات
    0.42
    btnDelete
    0.42
     favourite
    0.42
     hypotheses
    0.42
    AAD
    0.41
    がって
    0.41
     aima
    0.41
     hated
    0.40
     Business
    0.40
    Activations Density 0.034%

    No Known Activations