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. 8084
    Prev
    Next
    INDEX
    Explanations

    function and method calls related to user interface elements in programming

    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
    IUrlHelper
    -0.45
    parsedMessage
    -0.40
     listening
    -0.35
    DockStyle
    -0.35
     kasarigan
    -0.34
    ValueStyle
    -0.33
    __':
    -0.33
    onActivityResult
    -0.33
     slags
    -0.32
     onCreateView
    -0.31
    POSITIVE LOGITS
    PositiveButton
    0.90
    NegativeButton
    0.90
    bootstrapcdn
    0.61
     button
    0.60
     buttons
    0.59
    JButton
    0.56
     Button
    0.56
    QPushButton
    0.54
     Buttons
    0.54
    TextButton
    0.53
    Activations Density 0.011%

    No Known Activations