© 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. 21-GEMMASCOPE-RES-16K
    11. 11128
    Prev
    Next
    INDEX
    Explanations

    references to legal arguments and the adequacy of professional representation in a legal context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LEncoder
    -0.36
    createCanvas
    -0.34
     userSchema
    -0.31
    skraft
    -0.31
    ễ
    -0.30
    FTFY
    -0.30
    {!!
    -0.29
    TextBoxColumn
    -0.29
    Ễ
    -0.28
    fscanf
    -0.28
    POSITIVE LOGITS
     decisions
    0.86
    decisions
    0.80
     decision
    0.78
    decision
    0.74
     choices
    0.73
     choice
    0.73
     Decisions
    0.73
    Decisions
    0.72
     Choices
    0.70
    choices
    0.68
    Activations Density 0.983%

    No Known Activations