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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6350
    Prev
    Next
    INDEX
    Explanations

    legal terminology and structure in court documents

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     downvoted
    -0.30
     piece
    -0.30
     wikipagina
    -0.27
     bust
    -0.26
     native
    -0.25
     cra
    -0.24
     creep
    -0.24
     apparent
    -0.23
     blind
    -0.23
    közi
    -0.23
    POSITIVE LOGITS
    ChildScrollView
    0.78
    новништво
    0.75
     OFDb
    0.73
    ​
    0.71
     Италијани
    0.71
    ​​
    0.70
     مشين
    0.70
     Italijanski
    0.68
    ​​​​
    0.67
    ↵↵↵
    0.67
    Activations Density 1.083%

    No Known Activations