© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 53216
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific names related to places, people, or organizations

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

    military and defense contexts

    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
     समीक्षाओं
    -0.58
     snippetHide
    -0.47
    webElementGuid
    -0.43
    AdapterFactory
    -0.43
     frukt
    -0.42
    Hauptartikel
    -0.42
     surla
    -0.41
    PYX
    -0.41
     VIAF
    -0.41
    Tembelea
    -0.40
    POSITIVE LOGITS
     military
    1.15
     militaire
    1.07
    Military
    1.03
     Military
    1.03
    military
    1.00
     militar
    0.97
     militares
    0.94
     MILITARY
    0.94
     militaires
    0.92
     militare
    0.92
    Activations Density 0.081%

    No Known Activations