Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15266
    Prev
    Next
    INDEX
    Explanations

    references to comedians and comedic contexts in political discussions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Arque
    -0.61
    awtextra
    -0.58
    RenderAtEndOf
    -0.58
    Tazama
    -0.57
    useState
    -0.54
     démocratique
    -0.53
     héro
    -0.53
    isNaN
    -0.53
    ModelBuilder
    -0.53
     Treue
    -0.53
    POSITIVE LOGITS
     comedy
    1.32
     Comedy
    1.26
    comedy
    1.16
    Comedy
    1.15
     comedians
    1.13
     comedian
    1.09
     jokes
    1.01
     comedic
    0.97
     humor
    0.95
     funnier
    0.93
    Activations Density 0.118%

    No Known Activations