© 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. 20-GEMMASCOPE-RES-131K
    11. 102573
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to diversity and community engagement

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

    news channels, medical terms, specific organizations, jazz festivals, sports, military units

    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
     للمعارف
    -0.56
     detailsNormal
    -0.47
    setVerticalGroup
    -0.46
    المناصب
    -0.43
    ViewFeatures
    -0.41
    meanor
    -0.37
    Manbalar
    -0.36
    schöne
    -0.36
    锈钢
    -0.36
    رشف
    -0.35
    POSITIVE LOGITS
     gradova
    0.47
     GenerationType
    0.46
    autoreleasepool
    0.45
     etc
    0.45
     BorderRadius
    0.44
    bewerken
    0.43
    等等
    0.40
    StoryboardSegue
    0.40
     sebagainya
    0.40
    aratus
    0.40
    Activations Density 0.100%

    No Known Activations