© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 46892
    Prev
    Next
    INDEX
    Explanations

    references to specific films and their creators or notable elements related to comedy

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

    comedy and humor

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    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
    -0.64
    msgSender
    -0.54
     chuva
    -0.46
     Fotografía
    -0.46
     cabelos
    -0.45
     tacón
    -0.44
    setupUi
    -0.44
    seido
    -0.44
    fhir
    -0.43
    toHave
    -0.43
    POSITIVE LOGITS
     comedy
    0.84
     comedic
    0.79
     funnier
    0.79
     hilarious
    0.77
    comedy
    0.76
     Comedy
    0.75
     comedian
    0.75
     funniest
    0.72
    Comedy
    0.70
     hilar
    0.70
    Activations Density 0.029%

    No Known Activations