© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 13235
    Prev
    Next
    INDEX
    Explanations

    expressions of humor and comedic elements in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.63
     nakalista
    -0.58
    neté
    -0.55
    SharedDtor
    -0.54
     toekomst
    -0.50
     iprot
    -0.48
    Autoritní
    -0.47
     gekomen
    -0.47
     خارجية
    -0.46
    GTCX
    -0.46
    POSITIVE LOGITS
     humor
    2.47
     humorous
    2.45
     hilarious
    2.36
     jokes
    2.31
     joke
    2.27
     comedic
    2.27
     humour
    2.25
     comedy
    2.25
     funny
    2.16
     comical
    2.14
    Activations Density 0.319%

    No Known Activations