© 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. 4394
    Prev
    Next
    INDEX
    Explanations

    identifiers and parameters related to data structures or programming

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

    low-level technical or computational details related to message processing, memory addresses, and system-level operations.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    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
    存于互联网档案馆
    -0.72
    RenderAtEndOf
    -0.66
    󠁣
    -0.62
    OGND
    -0.62
    Билгалдахарш
    -0.60
    SourceChecksum
    -0.59
     estekak
    -0.57
    الإنجليزية
    -0.57
     Мексичка
    -0.57
    alakip
    -0.56
    POSITIVE LOGITS
    +#+
    0.43
    SPEC
    0.30
     politiques
    0.28
    sbereich
    0.28
     month
    0.27
    initialValue
    0.27
    spec
    0.27
    vänt
    0.27
    MeasureSpec
    0.26
    Integer
    0.26
    Activations Density 0.711%

    No Known Activations