© 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. 11-GEMMASCOPE-RES-16K
    11. 4819
    Prev
    Next
    INDEX
    Explanations

    terms related to statistical analysis and error measurement in research

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    辺
    -0.37
     growth
    -0.36
     Fe
    -0.35
     Ag
    -0.35
     Wal
    -0.34
    ⓧ
    -0.34
    rungsseite
    -0.34
     prop
    -0.33
     McMahon
    -0.33
     Lus
    -0.33
    POSITIVE LOGITS
    RenderAtEndOf
    0.82
     विश्वसनीयता
    0.69
     للاسماء
    0.65
    Билгалдахарш
    0.63
     Италијани
    0.63
    EDEFAULT
    0.62
    writeFieldEnd
    0.60
    ########.
    0.60
     שוליים
    0.59
     Autorizaciones
    0.59
    Activations Density 1.346%

    No Known Activations