© 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. 105464
    Prev
    Next
    INDEX
    Explanations

    terms and phrases relating to assessments of quality and understanding

    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
     Савезне
    -0.82
    EndProject
    -0.66
     Administrativna
    -0.63
     térmico
    -0.62
    expandindo
    -0.61
     Мексичка
    -0.61
    modelBuilder
    -0.59
    parsedMessage
    -0.57
    EndGlobalSection
    -0.56
    Personendaten
    -0.56
    POSITIVE LOGITS
     actionPerformed
    0.37
    BagConstraints
    0.35
     broad
    0.34
     related
    0.33
    ที
    0.31
    を見る
    0.29
     Gottes
    0.29
    Sch
    0.28
     specific
    0.28
     за
    0.28
    Activations Density 0.018%

    No Known Activations