© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4370
    Prev
    Next
    INDEX
    Explanations

    instances of laughter and humor in the text

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

    expressions of laughter and humor.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     propOrder
    -0.69
    الحياه
    -0.64
    ]")]
    -0.62
     للاسماء
    -0.59
     Wic
    -0.59
     nakalista
    -0.57
     tartalomajánló
    -0.56
     kasarigan
    -0.56
    routeProvider
    -0.56
    stateProvider
    -0.55
    POSITIVE LOGITS
     tertawa
    0.92
     laughed
    0.91
     laughing
    0.87
     laughter
    0.86
     laughs
    0.84
     laugh
    0.83
     Laugh
    0.77
    Laugh
    0.75
     risa
    0.71
     Laughing
    0.71
    Activations Density 0.035%

    No Known Activations