© 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. 41-GEMMASCOPE-RES-16K
    11. 4111
    Prev
    Next
    INDEX
    Explanations

    references to troubleshooting or solving technical issues

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     coö
    -1.01
     آن‌ها
    -0.94
     rôle
    -0.84
     می‌توان
    -0.83
     Māori
    -0.83
     می‌تواند
    -0.83
     Ō
    -0.79
     می‌
    -0.78
     résumé
    -0.77
     بی‌
    -0.77
    POSITIVE LOGITS
     Beyonce
    0.41
     cliche
    0.36
     ----
    0.36
     saute
    0.34
     Pokemon
    0.33
     didnt
    0.33
     ------
    0.33
     doesnt
    0.32
     --
    0.32
    ~~~~~~~~
    0.32
    Activations Density 9.374%

    No Known Activations