© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 334
    Prev
    Next
    INDEX
    Explanations

    elements related to coding and action creation in programming

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

    programming constructs related to action and function definitions

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

    action

    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
     ModelExpression
    -0.55
    ClientSize
    -0.54
    dersfield
    -0.51
    estimating
    -0.51
    ::$_
    -0.50
    UnifiedTopology
    -0.49
    Estimated
    -0.47
     Estimates
    -0.47
     interviewing
    -0.47
     certifying
    -0.47
    POSITIVE LOGITS
     action
    2.83
    action
    2.62
     Action
    2.56
    Action
    2.53
     ACTION
    2.46
     actions
    2.42
    ACTION
    2.41
     Actions
    2.32
    actions
    2.20
    Actions
    2.17
    Activations Density 0.061%

    No Known Activations