© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11321
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to judicial discretion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })`
    -0.43
     bio
    -0.37
    rungsseite
    -0.37
     '@/
    -0.37
    Xna
    -0.35
    basicConfig
    -0.34
    CardBody
    -0.33
     kare
    -0.33
    ={[
    -0.32
     Spre
    -0.32
    POSITIVE LOGITS
     Intern
    0.70
     intern
    0.69
    setVerticalGroup
    0.69
    Appendix
    0.66
     appendix
    0.66
     Appendix
    0.65
    Intern
    0.64
     Palmer
    0.64
    Palmer
    0.63
     Dock
    0.62
    Activations Density 1.074%

    No Known Activations