© 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. 41-GEMMASCOPE-RES-16K
    11. 5548
    Prev
    Next
    INDEX
    Explanations

    references to legal terminology or matters involving individuals and their status within the legal system

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

    No Comments

    Negative Logits
     users
    -1.56
     players
    -1.52
     borrowers
    -1.48
     patients
    -1.48
     customers
    -1.47
    users
    -1.45
     participants
    -1.44
     golfers
    -1.44
     residents
    -1.43
     consumers
    -1.43
    POSITIVE LOGITS
    öne
    0.40
    writeField
    0.39
    sproz
    0.38
     مرئيه
    0.37
    لاعات
    0.37
     caminhos
    0.37
     AssemblyCulture
    0.36
    OptionsMenu
    0.36
    Prints
    0.36
    Routes
    0.35
    Activations Density 2.266%

    No Known Activations