© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 40
    Prev
    Next
    INDEX
    Explanations

    the presence and variations of the keyword "Sho" and its related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     defaultstate
    -0.59
    ########.
    -0.58
    出版年
    -0.58
    featureID
    -0.55
    RegressionTest
    -0.52
     ArrayAdapter
    -0.52
    EndInit
    -0.50
    TintMode
    -0.50
    fillType
    -0.49
    awaiter
    -0.49
    POSITIVE LOGITS
     Sho
    2.56
    Sho
    2.47
    sho
    2.36
     sho
    2.22
     SHO
    1.70
    Scho
    1.37
    SHO
    1.36
     shopper
    1.35
     Scho
    1.33
     Шо
    1.29
    Activations Density 0.217%

    No Known Activations