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. 31-GEMMASCOPE-RES-16K
    6. 15783
    Prev
    Next
    INDEX
    Explanations

    components related to user interface elements in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Button press events or properties

    np_acts-logits-general · gemini-2.0-flash

    button press and activation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    下载附件
    -0.48
    parsedMessage
    -0.40
    
    -0.39
    DoubleQuotes
    -0.37
    AttributeSet
    -0.36
    Personendaten
    -0.35
    cstdio
    -0.35
    borderBottom
    -0.35
    Revenir
    -0.34
    findpost
    -0.34
    POSITIVE LOGITS
     pressed
    0.86
     press
    0.78
     Pressed
    0.75
    pressed
    0.74
     presses
    0.71
    Pressed
    0.71
     PRESS
    0.69
     pressing
    0.68
    pressing
    0.67
     button
    0.65
    Activations Density 0.157%

    No Known Activations