© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 11860
    Prev
    Next
    INDEX
    Explanations

    phrases related to scrolling or managing scroll position in a user interface

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

    scrolling

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    
    -0.51
    oa̍t
    -0.49
     ProtoMessage
    -0.49
     propOrder
    -0.47
     برانيه
    -0.47
     Chwiliwch
    -0.46
     chapéu
    -0.45
     चीज़ों
    -0.45
     cherchés
    -0.45
    slash
    -0.45
    POSITIVE LOGITS
     scroll
    1.77
     Scroll
    1.56
     scrolling
    1.53
    Scroll
    1.53
     scrolls
    1.49
    scroll
    1.41
     scrolled
    1.37
     Scrolls
    1.20
    croll
    1.16
    SCROLL
    1.16
    Activations Density 0.119%

    No Known Activations