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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 4465
    Prev
    Next
    INDEX
    Explanations

    references to vitamins and their health benefits, particularly vitamin C

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     خارجية
    -0.69
    PerformLayout
    -0.62
    principalTable
    -0.60
    таратура
    -0.59
    featureID
    -0.59
    ỡng
    -0.58
    :✨
    -0.57
    lossal
    -0.54
     kiel
    -0.54
    期刊论文
    -0.53
    POSITIVE LOGITS
     Peruvian
    0.62
    icoli
    0.61
     kaynağından
    0.58
     وتسجيلات
    0.56
     Oaxaca
    0.55
     häng
    0.55
     XSS
    0.55
     Gleaner
    0.54
     Adventist
    0.54
     peruano
    0.54
    Activations Density 1.179%

    No Known Activations