© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 12647
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to playful or inappropriate humor

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kontakta
    -0.50
     mnoho
    -0.49
     coute
    -0.49
     maîtrise
    -0.49
     voldoende
    -0.47
     nasional
    -0.46
     múltiple
    -0.46
     אשר
    -0.46
    attente
    -0.45
     számára
    -0.44
    POSITIVE LOGITS
     goofy
    1.04
     wacky
    0.99
    Demografie
    0.99
     darn
    0.96
     whack
    0.95
     peep
    0.94
     pesky
    0.94
     squishy
    0.93
     critters
    0.93
     funky
    0.92
    Activations Density 0.884%

    No Known Activations