© 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. 1277
    Prev
    Next
    INDEX
    Explanations

    formatting and punctuation elements within code snippets

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

    patterns in numerical or updated values within code or database queries

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

    code string concatenation

    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
    Hochspringen
    -0.71
     Theſe
    -0.68
    inken
    -0.65
     Connectez
    -0.64
     linkovi
    -0.64
    mergeFrom
    -0.63
     Beſ
    -0.61
     Anſ
    -0.60
    rrggbb
    -0.60
    +:+
    -0.60
    POSITIVE LOGITS
    rzost
    0.57
    endphp
    0.54
    ↵
    0.53
    StoryboardSegue
    0.52
    %");
    0.48
    Géographie
    0.46
    yntaxException
    0.45
    _));
    0.45
     encarga
    0.45
    VIAF
    0.44
    Activations Density 0.007%

    No Known Activations