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 - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15879
    Prev
    Next
    INDEX
    Explanations

    highly positive sentiments about Christmas-related elements and decorations

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

    "Christmas"

    np_acts-logits-general · gemini-2.0-flash

    Christmas holiday decorations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Chham
    -0.63
     StatelessWidget
    -0.51
     שוליים
    -0.50
    GTCX
    -0.49
     GenerationType
    -0.47
     للاسماء
    -0.47
     ویکی‌پدی
    -0.47
    новништво
    -0.46
     informée
    -0.46
    avadoc
    -0.46
    POSITIVE LOGITS
     Christmas
    1.78
    Christmas
    1.58
     christmas
    1.49
     holiday
    1.48
    🎄
    1.46
     CHRISTMAS
    1.41
     Xmas
    1.36
    christmas
    1.36
     festive
    1.34
     Weihnachts
    1.33
    Activations Density 0.090%

    No Known Activations