© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 41561
    Prev
    Next
    INDEX
    Explanations

    references to comedy and comedic elements

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

    stand-up comedy and comedy films

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    IntoConstraints
    -0.45
     Lordships
    -0.44
    istr
    -0.43
    Ashlee
    -0.43
    Natalia
    -0.42
     aquilo
    -0.42
     Picchu
    -0.41
    regarding
    -0.41
     BorderSide
    -0.40
     spirituale
    -0.40
    POSITIVE LOGITS
     Comedy
    1.08
    Comedy
    1.05
     comedy
    1.04
    comedy
    0.95
     comedians
    0.81
     comedian
    0.78
     comedies
    0.77
     comedic
    0.76
     comédie
    0.74
     Comédie
    0.69
    Activations Density 0.003%

    No Known Activations