Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15605
    Prev
    Next
    INDEX
    Explanations

    references to holidays and festive occasions

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

    Holidays and festivals

    np_acts-logits-general · gemini-2.0-flash

    holidays and celebrations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    السكان
    -0.56
    sizeCache
    -0.55
     dettaglio
    -0.53
     AssemblyProduct
    -0.53
     världen
    -0.52
    TemporalType
    -0.51
    المكان
    -0.49
     depic
    -0.49
    omitempty
    -0.49
     délé
    -0.49
    POSITIVE LOGITS
     Christmas
    2.27
     Thanksgiving
    2.00
     Halloween
    1.90
    Christmas
    1.88
     christmas
    1.86
     holiday
    1.86
     Easter
    1.85
     holidays
    1.82
     CHRISTMAS
    1.77
     Xmas
    1.74
    Activations Density 0.461%

    No Known Activations