© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 1716
    Prev
    Next
    INDEX
    Explanations

    references to comedians and comedic performances

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

    comedy and comedians

    np_acts-logits-general · gemini-2.0-flash

    comedy, comedian, joke

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     enged
    -0.63
     Arque
    -0.53
    useState
    -0.52
     vack
    -0.51
    GEBURTS
    -0.51
     marea
    -0.50
    owar
    -0.50
     sukker
    -0.50
     bParam
    -0.50
    válasz
    -0.48
    POSITIVE LOGITS
     comedy
    1.26
     Comedy
    1.25
    Comedy
    1.15
    comedy
    1.12
     comedians
    1.12
     comedian
    1.06
     comedic
    0.93
     funnier
    0.89
     comedia
    0.88
     jokes
    0.88
    Activations Density 0.151%

    No Known Activations