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

    Neuronpedia

    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
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 4906
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and events, particularly related to Christmas and holidays

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

    dates in the format of month/day or month-day with numerical values.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    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
     springtime
    -0.63
     spring
    -0.63
    Spring
    -0.57
    April
    -0.57
     Spring
    -0.56
    APRIL
    -0.54
     SPRING
    -0.54
    spring
    -0.53
     April
    -0.52
     primavera
    -0.52
    POSITIVE LOGITS
     Christmas
    1.62
    Christmas
    1.47
     christmas
    1.44
     CHRISTMAS
    1.43
    christmas
    1.40
     Xmas
    1.30
     xmas
    1.29
     December
    1.28
    🎄
    1.27
     Weihnachts
    1.23
    Activations Density 0.161%

    No Known Activations