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. 45706
    Prev
    Next
    INDEX
    Explanations

    references to Jewish cultural practices and traditions

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

    Jewish culture and traditions

    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
     للاسماء
    -0.59
     nahilalakip
    -0.58
     noDo
    -0.56
    Derbyniad
    -0.54
    +#+#
    -0.52
     ویکی‌آمباردا
    -0.52
    +#+
    -0.52
     laſſen
    -0.51
     contextLoads
    -0.51
    WireFormatLite
    -0.50
    POSITIVE LOGITS
     Jewish
    0.86
     Yiddish
    0.74
    Jewish
    0.73
    jewish
    0.66
     jüdis
    0.65
     Israeli
    0.64
     евре
    0.64
     Jews
    0.64
     Hebrew
    0.63
     Passover
    0.60
    Activations Density 0.082%

    No Known Activations