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-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16259
    Prev
    Next
    INDEX
    Explanations

    references to medicinal or edible plant properties

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

    scientific language about medicinal plants, their uses, and nutritional properties.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oneofs
    -0.42
    worpen
    -0.33
     poš
    -0.33
     jsPsych
    -0.32
    pædia
    -0.32
    isContained
    -0.31
     bambou
    -0.30
     nahilalakip
    -0.30
     dimiliki
    -0.30
     typename
    -0.30
    POSITIVE LOGITS
    食用
    0.71
     medicinal
    0.71
     ornamental
    0.69
     culinary
    0.67
    industrial
    0.66
     cosmetics
    0.65
    decorative
    0.65
     Medicinal
    0.64
     decorative
    0.62
     industrial
    0.61
    Activations Density 0.553%

    No Known Activations