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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 853
    Prev
    Next
    INDEX
    Explanations

    instances of laughter and comedic expressions

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

    laughter

    np_acts-logits-general · gemini-2.0-flash

    amused laughter

    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
     Par
    -0.46
     Res
    -0.46
    éez
    -0.45
    RegistryLite
    -0.43
    Res
    -0.43
    grés
    -0.42
    пон
    -0.42
     Kens
    -0.42
     utara
    -0.41
     Tip
    -0.41
    POSITIVE LOGITS
    expandindo
    0.89
     laughter
    0.80
     Laughter
    0.80
     laugh
    0.79
     laughing
    0.78
     Laugh
    0.76
     lachen
    0.74
     Laughing
    0.73
     laughed
    0.73
     hyster
    0.73
    Activations Density 0.044%

    No Known Activations