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. 24-GEMMASCOPE-RES-131K
    6. 1049
    Prev
    Next
    INDEX
    Explanations

    references to scrolling behavior in web interfaces

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

    scrolling logs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ey
    -0.55
    ian
    -0.52
    ians
    -0.51
    er
    -0.48
     Infórmanos
    -0.47
     Nature
    -0.46
    Than
    -0.46
     Vay
    -0.46
    Ma
    -0.44
     Than
    -0.44
    POSITIVE LOGITS
    crollView
    0.99
    scroll
    0.98
    croll
    0.93
     scroll
    0.93
     Scroll
    0.92
    Scroll
    0.92
     scrolls
    0.85
    SCROLL
    0.81
     Scrolls
    0.77
    scrolling
    0.75
    Activations Density 0.003%

    No Known Activations