© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3794
    Prev
    Next
    INDEX
    Explanations

    humorous and comical language

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

    emotional or subjective reactions, like feeling amused, entertaining, or lighthearted.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    expressions of humor and amusement, including laughter interjections, emoticons, and descriptions of a light‑hearted, not‑too‑serious tone.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408

    informal, conversational expressions of amusement or lightheartedness, often with qualifiers like "amusing," "amused," "lol," or phrases that soften or dismiss seriousness.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408
    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
    PTSD
    -0.40
    mergeFrom
    -0.40
    PointerException
    -0.39
     ſte
    -0.38
    Портали
    -0.38
    AddTagHelper
    -0.37
    StoryboardSegue
    -0.36
     سک
    -0.35
     Holocaust
    -0.34
    rrggbb
    -0.34
    POSITIVE LOGITS
     humorous
    1.04
     hilarious
    0.99
     comical
    0.96
     amusing
    0.93
     laugh
    0.91
     funny
    0.90
     humor
    0.87
     funniest
    0.81
     laughing
    0.81
     chuckled
    0.80
    Activations Density 0.171%

    No Known Activations