© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 104812
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names, particularly those related to places, people, or cultural references

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Negative Logits
    ldquo
    -0.57
     فريبيس
    -0.56
    XtraReports
    -0.55
    存于互联网档案馆
    -0.52
    writeFieldEnd
    -0.51
     Bens
    -0.50
    CPC
    -0.49
     tbs
    -0.48
     karş
    -0.48
    truc
    -0.48
    POSITIVE LOGITS
    ey
    1.14
    ay
    1.08
    AY
    0.91
    oy
    0.88
     AY
    0.82
    uy
    0.82
     Ley
    0.81
     Cay
    0.81
    Ley
    0.79
     Tay
    0.78
    Activations Density 0.068%

    No Known Activations