© 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. 1289
    Prev
    Next
    INDEX
    Explanations

    references to file paths and operations related to file management

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

    references to the operating system and file path operations in code

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

    . join, objectives of

    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
    Παραπομπές
    -0.53
    TemporalType
    -0.50
    GTCX
    -0.47
    writeInt
    -0.47
     noqa
    -0.45
    %^
    -0.45
    "}")
    -0.45
     verwijzen
    -0.44
     secret
    -0.44
    )++;
    -0.44
    POSITIVE LOGITS
    join
    0.70
     join
    0.58
    sprintf
    0.57
    MigrationBuilder
    0.54
     namelijk
    0.53
    mybatisplus
    0.53
    ArgsConstructor
    0.52
    expandindo
    0.52
    limits
    0.52
     sprintf
    0.51
    Activations Density 0.009%

    No Known Activations