© 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. 588
    Prev
    Next
    INDEX
    Explanations

    keys in programming and data structures

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

    elements related to programming or coding structures, particularly those related to method signatures and collections

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

    answer or study

    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
    ?
    -0.61
     ?
    -0.53
     en
    -0.50
     >>
    -0.50
     …
    -0.49
     T
    -0.47
     du
    -0.46
     @
    -0.46
    =-
    -0.45
    colorPrimary
    -0.45
    POSITIVE LOGITS
     myſelf
    0.95
    ſelves
    0.84
    enumi
    0.82
     Anſ
    0.82
    tvguidetime
    0.81
     Majefty
    0.80
     समीक्षक
    0.79
     itſelf
    0.78
    ſelf
    0.78
     ſhe
    0.78
    Activations Density 0.015%

    No Known Activations