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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 16090
    Prev
    Next
    INDEX
    Explanations

    CSS and layout-related properties and attributes

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

    HTML image width attribute

    np_acts-logits-general · gemini-2.0-flash

    width properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    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
     تضيفلها
    -0.41
     hatches
    -0.36
    ยก
    -0.36
    paddingTop
    -0.35
     fence
    -0.34
    仰
    -0.34
     atop
    -0.33
    uplo
    -0.33
     capo
    -0.32
     refers
    -0.32
    POSITIVE LOGITS
    تقاوى
    0.73
     للمعارف
    0.70
    astéroïdes
    0.68
    JspWriter
    0.65
     width
    0.60
    ChildScrollView
    0.59
     EconPapers
    0.58
     MainAxisSize
    0.57
    __(/*!
    0.56
     getWidth
    0.55
    Activations Density 0.088%

    No Known Activations