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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 102977
    Prev
    Next
    INDEX
    Explanations

    instances of special formatting or markup within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    PerformLayout
    -0.49
    InputBorder
    -0.46
     onCreateView
    -0.45
    centralwidget
    -0.44
     ThemeData
    -0.41
    orianCalendar
    -0.40
    gway
    -0.39
    savevideobot
    -0.38
    PREFERRED
    -0.38
    createStatement
    -0.38
    POSITIVE LOGITS
    EndGlobalSection
    0.75
    WebElementEntity
    0.68
    IndentedString
    0.65
    EndProject
    0.57
    msgTypes
    0.56
    oredCriteria
    0.54
    NameInMap
    0.54
    windowFixed
    0.48
    transQ
    0.47
    astéroïdes
    0.47
    Activations Density 0.001%

    No Known Activations