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-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 84505
    Prev
    Next
    INDEX
    Explanations

    HTML div elements and their attributes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.41
    addCriterion
    -0.41
     المعيارى
    -0.38
    antMatchers
    -0.38
    MethodManager
    -0.36
    putExtra
    -0.36
    apiClient
    -0.36
    +:+
    -0.35
    迁
    -0.34
    __":
    -0.34
    POSITIVE LOGITS
    aarrggbb
    0.59
     autorytatywna
    0.49
     informée
    0.48
    WebElementEntity
    0.48
    RenderAtEndOf
    0.47
     facelift
    0.47
    ніципалі
    0.46
     ویکی‌پدی
    0.45
     perles
    0.44
     HttpNotFound
    0.44
    Activations Density 0.012%

    No Known Activations