Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 413
    Prev
    Next
    INDEX
    Explanations

    certain programming or syntax elements related to definitions and classifications

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

    hexadecimal numbers and technical/programming notation.

    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
    帖最后由
    -0.26
     próximas
    -0.24
     not
    -0.23
     Freunde
    -0.23
     Demokratie
    -0.21
     próxima
    -0.20
     using
    -0.20
    ’
    -0.20
     a
    -0.20
     Desarrollo
    -0.20
    POSITIVE LOGITS
    RenderAtEndOf
    0.95
    IsMutable
    0.86
    uxxxx
    0.85
    iſten
    0.85
     ſehr
    0.84
     AttributeSet
    0.84
     MainAxisSize
    0.84
    iſche
    0.82
    оргаш
    0.82
     Geſch
    0.81
    Activations Density 0.882%

    No Known Activations