Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 3776
    Prev
    Next
    INDEX
    Explanations

    quantitative data, specifically numerical values and percentages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EndGlobalSection
    -0.47
     للاسماء
    -0.45
    devamını
    -0.45
     кӀош
    -0.39
     noDo
    -0.37
     ویکی‌پدی
    -0.37
    erà
    -0.36
    下载附件
    -0.36
    ستاگرام
    -0.36
     allá
    -0.36
    POSITIVE LOGITS
     metres
    0.66
     kilometres
    0.65
     litres
    0.64
     acres
    0.62
     pounds
    0.62
     metre
    0.60
     kilometre
    0.60
     gallons
    0.58
     kilometers
    0.57
     ounces
    0.57
    Activations Density 2.365%

    No Known Activations