© 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. 0-GEMMASCOPE-RES-16K
    11. 4214
    Prev
    Next
    INDEX
    Explanations

    instances of humor or jokes within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     filo
    -0.53
    ----------------
    -0.45
    estras
    -0.45
     transcription
    -0.43
    odendron
    -0.43
    optString
    -0.43
     allem
    -0.43
     deep
    -0.43
     dir
    -0.42
     en
    -0.41
    POSITIVE LOGITS
     joke
    1.54
     Jokes
    1.51
     jokes
    1.49
     laughs
    1.41
     laughed
    1.41
    Jokes
    1.35
     funniest
    1.33
     joked
    1.32
     laugh
    1.29
     humorous
    1.29
    Activations Density 2.537%

    No Known Activations