© 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. 37-GEMMASCOPE-RES-16K
    11. 8954
    Prev
    Next
    INDEX
    Explanations

    references to legal proceedings and judgments

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    دانشنامهٔ
    -0.90
     témoig
    -0.80
     belongs
    -0.78
     fashiola
    -0.77
    ſſung
    -0.77
    قایناق‌لار
    -0.77
    
    -0.77
    <unused52>
    -0.76
    <unused21>
    -0.75
    <unused28>
    -0.75
    POSITIVE LOGITS
     sommes
    0.40
     jesteśmy
    0.40
     jestem
    0.35
     are
    0.33
     jesteś
    0.30
    Estoy
    0.29
     êtes
    0.28
     suis
    0.28
     estés
    0.23
     estar
    0.23
    Activations Density 0.806%

    No Known Activations