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-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 7119
    Prev
    Next
    INDEX
    Explanations

    terms related to advanced mathematical concepts and equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Folsom
    -1.02
    ={({
    -1.02
    Портал
    -1.02
     Presley
    -1.02
     Dordrecht
    -0.94
     Presby
    -0.92
    chium
    -0.90
     Arki
    -0.88
     Diſ
    -0.87
     {?>
    -0.87
    POSITIVE LOGITS
     Duffy
    0.73
    HEET
    0.71
    мпу
    0.70
    Duff
    0.69
     Tas
    0.69
    Sheets
    0.69
     SHEET
    0.68
     lamb
    0.68
     lambs
    0.67
     Lam
    0.67
    Activations Density 0.806%

    No Known Activations