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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 4190
    Prev
    Next
    INDEX
    Explanations

    instances of humor and comedic expressions

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

    Humor, jokes, and lightheartedness

    np_acts-logits-general · gemini-2.0-flash

    humorous, funny, laughs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ьаж
    -0.59
     دیکھیے
    -0.55
    tuan
    -0.51
    ActivityCompat
    -0.48
     мәкал
    -0.47
     сожалению
    -0.47
    OwnProperty
    -0.47
    ształ
    -0.45
     oprot
    -0.45
     persoons
    -0.45
    POSITIVE LOGITS
     humor
    2.38
     laugh
    2.37
     humorous
    2.33
     jokes
    2.31
     laughs
    2.29
     humour
    2.28
     joke
    2.27
     laughing
    2.26
     laughter
    2.24
     hilarious
    2.20
    Activations Density 0.615%

    No Known Activations