© 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. 1292
    Prev
    Next
    INDEX
    Explanations

    terms related to collaboration and management

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

    references to organizational structures and roles within a formal system or entities

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

    listing and continuation

    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
    /
    -0.86
    -/
    -0.74
     /
    -0.73
    ／
    -0.69
     '/';
    -0.66
     "/";
    -0.63
    /
    -0.63
    /');
    -0.61
    ;/
    -0.60
    /:
    -0.60
    POSITIVE LOGITS
     etc
    0.96
    etc
    0.79
     usw
    0.78
    !*\
    0.70
     stb
    0.70
     Etc
    0.69
     ete
    0.68
    migrationBuilder
    0.67
    +#+#
    0.66
     등
    0.64
    Activations Density 0.513%

    No Known Activations