© 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 EvalsExportsinterp-engineNEWAPI 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. 112001
    Prev
    Next
    INDEX
    Explanations

    references to Christmas and its related events

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

    Christmas activities and items

    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
    voerd
    -0.48
     abbiano
    -0.41
     fossero
    -0.41
     alça
    -0.41
     Sully
    -0.40
     siano
    -0.40
    AllowUser
    -0.39
     گفتم
    -0.39
     Autorin
    -0.39
     pulseira
    -0.39
    POSITIVE LOGITS
     Christmas
    1.30
    Christmas
    1.29
     CHRISTMAS
    1.20
     christmas
    1.17
    ristmas
    1.13
    christmas
    1.13
     xmas
    0.97
     Xmas
    0.94
    ihnachts
    0.90
     Navidad
    0.88
    Activations Density 0.003%

    No Known Activations