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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 12420
    Prev
    Next
    INDEX
    Explanations

    special occasions and celebrations associated with holidays

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

    Holidays and celebrations

    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 @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CPtr
    -0.59
    //
    -0.56
    ->$
    -0.54
    Портал
    -0.50
     født
    -0.47
    ransition
    -0.46
    hassee
    -0.45
     Turner
    -0.44
    APTER
    -0.43
    enosti
    -0.43
    POSITIVE LOGITS
     celebrations
    0.82
    addGap
    0.75
     tartalomajánló
    0.72
     celebration
    0.69
     '\\;'
    0.68
     CGSize
    0.67
     Eve
    0.66
     eve
    0.66
     Celebrations
    0.66
    Celebr
    0.65
    Activations Density 0.115%

    No Known Activations