© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8001
    Prev
    Next
    INDEX
    Explanations

    elements related to humor and comedy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IContainer
    -0.96
    AndEndTag
    -0.76
    GEBURTS
    -0.76
    migrationBuilder
    -0.70
    ecore
    -0.69
    iotensin
    -0.69
    новништво
    -0.69
     الاطلاع
    -0.66
     surla
    -0.66
     ویکی‌پدیا
    -0.65
    POSITIVE LOGITS
     humor
    2.36
     comedy
    2.33
     Comedy
    2.17
     Humor
    2.14
    humor
    2.06
     comedic
    2.06
     humour
    2.04
    Humor
    2.00
    comedy
    1.95
    Comedy
    1.94
    Activations Density 0.090%

    No Known Activations