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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 4587
    Prev
    Next
    INDEX
    Explanations

    data related to educational statistics and institutional information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     twenty
    -0.62
     thirty
    -0.61
    二十
    -0.60
     forty
    -0.60
    Twenty
    -0.59
     Twenty
    -0.58
    Forty
    -0.57
     TWENTY
    -0.57
    twenty
    -0.56
     vingt
    -0.56
    POSITIVE LOGITS
     thousand
    1.05
     thousands
    1.02
    thousands
    0.95
     Thousands
    0.95
    Thousands
    0.93
     THOUS
    0.92
     Thousand
    0.89
    三千
    0.85
    thousand
    0.84
    Thousand
    0.84
    Activations Density 0.832%

    No Known Activations