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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 15-GEMMASCOPE-RES-16K
    6. 1537
    Prev
    Next
    INDEX
    Explanations

    nutritional information related to vitamins and minerals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -0.85
    ſelves
    -0.77
     Efq
    -0.77
    хьтан
    -0.75
     ſhall
    -0.73
     myſelf
    -0.72
     chofe
    -0.71
     CreateTagHelper
    -0.70
     uſed
    -0.66
     raiſ
    -0.65
    POSITIVE LOGITS
     Vitamin
    0.69
     vitamin
    0.68
    पया
    0.65
     antioxidants
    0.62
    Vitamin
    0.61
     antioxidant
    0.55
     vitamins
    0.54
     Vitamins
    0.54
    oxidants
    0.52
     healing
    0.52
    Activations Density 0.198%

    No Known Activations