© 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. 20-GEMMASCOPE-RES-16K
    11. 4660
    Prev
    Next
    INDEX
    Explanations

    textual indicators of legal terms and conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    computer programming syntax and code-related tokens.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikimedijinoj
    -0.83
     ModelExpression
    -0.81
    aarrggbb
    -0.78
     betweenstory
    -0.78
    kloped
    -0.76
    <unused8>
    -0.75
    <unused3>
    -0.75
    <unused43>
    -0.74
    <unused41>
    -0.74
    <unused16>
    -0.74
    POSITIVE LOGITS
     siitä
    0.32
     abenço
    0.32
     tästä
    0.30
     aanwezig
    0.29
    but
    0.28
     sija
    0.28
    this
    0.28
     satunya
    0.28
     without
    0.27
     
    0.27
    Activations Density 0.130%

    No Known Activations