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. 4-GEMMASCOPE-RES-16K
    6. 15971
    Prev
    Next
    INDEX
    Explanations

    expressions and discussions related to laughter and humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    []{"
    -0.67
    例句
    -0.66
    stvo
    -0.64
    =@"
    -0.62
    ://"
    -0.62
    ibin
    -0.61
    ,:);
    -0.60
    ==='
    -0.60
    {'
    -0.59
    ,:),
    -0.59
    POSITIVE LOGITS
     laugh
    2.04
     laughs
    1.89
     laughter
    1.80
     laughed
    1.75
     laughing
    1.75
     Laughter
    1.70
     Laugh
    1.61
     Laughing
    1.56
     funny
    1.44
     jokes
    1.43
    Activations Density 0.071%

    No Known Activations