© 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. 23271
    Prev
    Next
    INDEX
    Explanations

    references to religious or spiritual themes related to Jewish practices and traditions

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

    ancient Jewish practice

    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
    Rohy
    -0.66
     disambiguazione
    -0.63
    脚注の使い方
    -0.60
    Datuak
    -0.59
    Aholisi
    -0.58
     <=",
    -0.57
     AppCompatTheme
    -0.57
     noDo
    -0.55
     ModelExpression
    -0.55
    Tikang
    -0.54
    POSITIVE LOGITS
     fundos
    0.35
     probabilmente
    0.34
     probably
    0.34
    ब्द
    0.33
     provavelmente
    0.31
     ter
    0.31
     typical
    0.31
    דול
    0.31
     monedas
    0.28
     royal
    0.28
    Activations Density 0.017%

    No Known Activations