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. 6322
    Prev
    Next
    INDEX
    Explanations

    instructions related to mouse clicks, particularly right-click actions in a user interface

    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
    OrBuilder
    -0.50
    yntaxException
    -0.48
    DebuggerStep
    -0.47
    bgp
    -0.47
    migrationBuilder
    -0.46
    PropertyChanging
    -0.46
    Formik
    -0.46
    ⏪
    -0.45
    skjaer
    -0.45
     Poverty
    -0.42
    POSITIVE LOGITS
    JMenuItem
    0.85
     JMenuItem
    0.75
     onOptions
    0.67
    JMenu
    0.60
    MenuItem
    0.52
    OptionsMenu
    0.52
     MenuItem
    0.50
    menuStrip
    0.49
    SubMenu
    0.48
    featureID
    0.47
    Activations Density 0.146%

    No Known Activations