Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 7457
    Prev
    Next
    INDEX
    Explanations

    user interface elements related to buttons and commands in programming contexts

    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-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
    SceneManagement
    -0.56
    zień
    -0.49
     wikipagina
    -0.47
    StateToProps
    -0.46
    readAll
    -0.45
    Citiți
    -0.45
    ResumeLayout
    -0.45
     réal
    -0.44
    >({
    -0.44
    (@"%@",
    -0.43
    POSITIVE LOGITS
     IconButton
    2.14
    IconButton
    1.95
     InputDecoration
    0.70
    ListItemIcon
    0.63
     AssemblyCulture
    0.60
    LabelTagHelper
    0.56
     فريبيس
    0.56
    tagHelperRunner
    0.56
    httphttps
    0.54
    RenderAtEndOf
    0.53
    Activations Density 0.000%

    No Known Activations