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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 2213
    Prev
    Next
    INDEX
    Explanations

    code related to scroll position modifications in a web context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DMETHOD
    -0.41
     stanovnika
    -0.34
     club
    -0.34
    BeginInit
    -0.33
     &=&
    -0.32
     stu
    -0.31
     pola
    -0.31
    Ӕ
    -0.31
    =$?
    -0.31
    Pautan
    -0.30
    POSITIVE LOGITS
    ChildScrollView
    0.96
    crollView
    0.93
     scrolls
    0.62
    ScrollView
    0.58
    scroll
    0.57
    aarrggbb
    0.56
    findpost
    0.55
     Scrolls
    0.54
    croll
    0.52
    ScrollBar
    0.52
    Activations Density 0.119%

    No Known Activations