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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 1556
    Prev
    Next
    INDEX
    Explanations

    references to button elements in a programming context

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

    The literal word "button"

    np_acts-logits-general · gemini-2.0-flash

    UI button elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NgModule
    -0.79
    windowFixed
    -0.74
    GetEnumerator
    -0.72
    OrWhiteSpace
    -0.71
    glLoadIdentity
    -0.71
     Gracia
    -0.70
    {?>
    -0.66
    BeginInit
    -0.65
    erweise
    -0.65
    PropertyChanging
    -0.65
    POSITIVE LOGITS
     buttons
    1.82
     Buttons
    1.63
     button
    1.51
     Button
    1.51
    buttons
    1.48
     BUTTON
    1.47
    Buttons
    1.44
    button
    1.36
     btn
    1.26
    BUTTON
    1.25
    Activations Density 0.089%

    No Known Activations