© 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. 33-GEMMASCOPE-RES-16K
    11. 3236
    Prev
    Next
    INDEX
    Explanations

    references to racial identity and the historical context of slavery

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Билгалдахарш
    -0.49
    UnusedPrivate
    -0.48
    
    -0.43
    ISupport
    -0.42
    centralwidget
    -0.39
    ViewImports
    -0.36
    timents
    -0.35
     Gegens
    -0.34
     الوق
    -0.33
    Datuak
    -0.32
    POSITIVE LOGITS
     refuses
    1.91
     refuse
    1.77
     refused
    1.73
     refusing
    1.70
     refusal
    1.65
     Refuse
    1.41
     refus
    1.41
     refusé
    1.40
     won
    1.38
    不肯
    1.30
    Activations Density 0.513%

    No Known Activations