© 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. 661
    Prev
    Next
    INDEX
    Explanations

    programmatic import statements in a codebase

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

    lines of code related to import statements in programming

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

    import io

    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
    webElement
    -0.49
    بار
    -0.46
    tomb
    -0.45
    pat
    -0.45
     насеље
    -0.43
    ent
    -0.42
    peg
    -0.41
    ella
    -0.41
     ?>>
    -0.40
    ''
    -0.39
    POSITIVE LOGITS
     org
    0.84
     estekak
    0.73
     ORG
    0.72
     Org
    0.70
    #+#
    0.66
    IBOutlet
    0.65
    WithIOException
    0.65
     orgánica
    0.64
     fieldNum
    0.64
    casque
    0.62
    Activations Density 0.006%

    No Known Activations