© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1032
    Prev
    Next
    INDEX
    Explanations

    sequences of alphanumeric characters, likely identifying unique identifiers or codes

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

    URLs or long strings of text with technical characters, particularly from web or file paths.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    alphanumeric hash-like ID strings, especially those embedded in URLs or file/resource paths.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    random alphanumeric strings, particularly base64-encoded data or URL-safe identifiers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ValueStyle
    -0.83
     Chwiliwch
    -0.78
    IntoConstraints
    -0.75
    )))),
    -0.69
     kasarigan
    -0.65
    rungsseite
    -0.60
    expandindo
    -0.59
    :+:
    -0.59
     ModelExpression
    -0.57
    帖最后由
    -0.57
    POSITIVE LOGITS
    file
    0.38
    K
    0.32
     Roswell
    0.31
    digan
    0.31
    sk
    0.31
    j
    0.31
    ga
    0.31
    kwij
    0.31
    ne
    0.31
    ystis
    0.30
    Activations Density 0.092%

    No Known Activations