© 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. 8-GEMMASCOPE-RES-16K
    11. 15220
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with 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 @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tlere
    -0.63
     Borden
    -0.60
    ésia
    -0.58
    usepackage
    -0.57
    migrationBuilder
    -0.57
    CreateModel
    -0.56
    itors
    -0.56
    ட்டி
    -0.56
     agence
    -0.55
     Rossi
    -0.54
    POSITIVE LOGITS
     Laughter
    1.43
     laugh
    1.40
     Laugh
    1.39
     laughter
    1.36
     laughing
    1.29
     Laughing
    1.25
     laughs
    1.24
     laughed
    1.12
    laugh
    1.10
     lachen
    1.08
    Activations Density 0.043%

    No Known Activations