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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45897
    Prev
    Next
    INDEX
    Explanations

    elements and structure in programming code

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

    code comparisons and type checking

    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
    StoryboardSegue
    -0.75
    transQ
    -0.68
    awaiter
    -0.66
    AndEndTag
    -0.65
    webElementXpaths
    -0.64
    tagext
    -0.62
    posedge
    -0.61
     吋
    -0.60
    AddHtmlAttribute
    -0.59
    الحياه
    -0.59
    POSITIVE LOGITS
     Eintrag
    0.35
    ckså
    0.31
    thodoxy
    0.31
     EClass
    0.28
    парта
    0.27
     autorytatywna
    0.27
    []
    0.26
    Buck
    0.26
    NB
    0.25
    PN
    0.25
    Activations Density 0.001%

    No Known Activations