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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 61819
    Prev
    Next
    INDEX
    Explanations

    the word "study" and related descriptors indicating the purpose or findings of research

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

    scientific research and studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     تضيفلها
    -0.56
     يتيمه
    -0.45
    pters
    -0.42
     الرياضيه
    -0.42
    UnsafeEnabled
    -0.40
    :✨
    -0.40
    WebElementEntity
    -0.39
    MethodManager
    -0.39
    OptionsMenu
    -0.38
    mobileqq
    -0.37
    POSITIVE LOGITS
    참고
    0.75
     research
    0.71
     researchers
    0.70
     scientist
    0.68
     researcher
    0.67
     researches
    0.67
     scientists
    0.66
     study
    0.65
     studies
    0.60
     onderzoek
    0.59
    Activations Density 0.243%

    No Known Activations