© 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. 102805
    Prev
    Next
    INDEX
    Explanations

    mathematical operations and their components in formal expressions

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

    assigning variables

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Roskov
    -0.79
    delwed
    -0.69
    AndEndTag
    -0.68
     незавершена
    -0.65
    ScopeManager
    -0.64
     ब्रेकडाउन
    -0.63
    uxxxx
    -0.62
    IntoConstraints
    -0.61
    keyColumn
    -0.60
    ViewImports
    -0.60
    POSITIVE LOGITS
     disfr
    0.33
     afectado
    0.31
     notably
    0.29
    forhold
    0.28
     kaupung
    0.28
     écoles
    0.28
     added
    0.27
     ebenfalls
    0.27
     disfru
    0.27
     szint
    0.27
    Activations Density 0.235%

    No Known Activations