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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 362
    Prev
    Next
    INDEX
    Explanations

    references to modified starch and related scientific analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    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
    dicionado
    -0.69
    новниш
    -0.66
     ویکی‌پدیا
    -0.66
    TintMode
    -0.64
    TargetException
    -0.62
    ništvo
    -0.62
     ſmall
    -0.61
     Monfieur
    -0.61
     HasFactory
    -0.61
     noDo
    -0.61
    POSITIVE LOGITS
     ModelExpression
    0.59
     Our
    0.55
    Our
    0.53
    ्रीय
    0.52
    +#+#
    0.47
    WarningLevel
    0.46
     }}">
    0.46
    main
    0.45
     än
    0.44
     im
    0.43
    Activations Density 0.005%

    No Known Activations