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. 20-GEMMASCOPE-RES-16K
    6. 8694
    Prev
    Next
    INDEX
    Explanations

    components related to web development and user interface design

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    RTCF
    -0.30
     farine
    -0.28
    页面存档备份
    -0.26
     vatt
    -0.26
     searching
    -0.25
    PickerController
    -0.25
    TextMessage
    -0.24
    )))))
    -0.24
     silent
    -0.24
     recording
    -0.24
    POSITIVE LOGITS
    InputBorder
    0.73
    bootstrapcdn
    0.66
     للاسماء
    0.64
    :✨
    0.64
     ModelExpression
    0.62
     TextAppearance
    0.62
    WebElementEntity
    0.61
    IntoConstraints
    0.61
    AnimationsModule
    0.60
    ViewImports
    0.59
    Activations Density 0.198%

    No Known Activations