© 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. 40-GEMMASCOPE-RES-16K
    11. 8798
    Prev
    Next
    INDEX
    Explanations

    legal and procedural terms related to court rulings and defendant rights

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     définitivement
    -0.57
     manualmente
    -0.56
    correctly
    -0.56
     corretamente
    -0.56
     automatiquement
    -0.56
     correctamente
    -0.54
     régulièrement
    -0.54
     Regularly
    -0.54
     rapidamente
    -0.54
     gärna
    -0.54
    POSITIVE LOGITS
     direct
    0.88
     simultaneous
    0.79
     immediate
    0.76
     effective
    0.76
     prompt
    0.74
     systematic
    0.74
     sustained
    0.72
     purposeful
    0.72
     continuous
    0.70
     unrestricted
    0.69
    Activations Density 1.379%

    No Known Activations