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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 14130
    Prev
    Next
    INDEX
    Explanations

    references to layout configurations in a graphical or programming context

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

    layout

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ویکی‌پدی
    -0.61
     henkil
    -0.56
    ennemi
    -0.55
     médicale
    -0.55
     étranger
    -0.53
    astéro
    -0.51
     extranjera
    -0.49
     cinquième
    -0.49
    withCredentials
    -0.48
     tenisky
    -0.48
    POSITIVE LOGITS
     Layout
    1.48
     layout
    1.41
     LAYOUT
    1.39
    Layout
    1.39
    layout
    1.35
    LAYOUT
    1.26
     layouts
    1.22
    ayout
    1.12
    getLayout
    1.07
     getLayout
    1.04
    Activations Density 0.007%

    No Known Activations