© 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. 36-GEMMASCOPE-RES-16K
    11. 5181
    Prev
    Next
    INDEX
    Explanations

    key legal terms and concepts related to court rulings and judicial decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.48
     atitude
    -0.41
     judgement
    -0.40
     visualisation
    -0.38
     jul
    -0.37
     practised
    -0.37
     astu
    -0.37
     بيها
    -0.37
     organisation
    -0.36
    Chham
    -0.36
    POSITIVE LOGITS
     pursuant
    0.84
     Pursuant
    0.75
     Plaintiffs
    0.68
     Defendants
    0.67
     contemporaneous
    0.67
     Defendant
    0.65
     effectu
    0.64
     decedent
    0.64
    Defendant
    0.63
     thereunder
    0.63
    Activations Density 7.865%

    No Known Activations