© 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. 0-GEMMASCOPE-RES-65K
    11. 10030
    Prev
    Next
    INDEX
    Explanations

    sequences of quotation marks and associated characters in a code or text format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     G
    -0.52
     the
    -0.51
     R
    -0.47
     a
    -0.47
     and
    -0.46
     in
    -0.46
     of
    -0.45
     L
    -0.45
     N
    -0.45
     ver
    -0.45
    POSITIVE LOGITS
    ".
    2.97
    "}
    2.91
    )".
    2.88
    ?"
    2.83
    ")
    2.80
    )"
    2.80
    "?
    2.78
    ,"
    2.75
    )."
    2.75
    '".
    2.73
    Activations Density 0.673%

    No Known Activations