© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 16010
    Prev
    Next
    INDEX
    Explanations

    references to the "Holy" as it relates to religious contexts or entities

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

    Holy Roman

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     typelib
    -0.63
    LabelTagHelper
    -0.60
    ésultats
    -0.60
     Irán
    -0.56
    CPtr
    -0.55
     Ucrania
    -0.55
    plasia
    -0.54
    Botswana
    -0.54
     שלהם
    -0.54
     Jeans
    -0.53
    POSITIVE LOGITS
     Holy
    1.95
    Holy
    1.80
     HOLY
    1.54
     holy
    1.36
    holy
    1.33
    HOLY
    1.33
     Heiligen
    0.96
     Heilige
    0.88
     Holly
    0.88
    Holly
    0.78
    Activations Density 0.005%

    No Known Activations