© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14047
    Prev
    Next
    INDEX
    Explanations

    social interactions characterized by humor and playful banter

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

    Humor and jokes

    np_acts-logits-general · gemini-2.0-flash

    joking and pranks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ngdoc
    -0.35
     invokingState
    -0.29
    ']))
    -0.28
     esfuerzos
    -0.28
     miraculously
    -0.27
     maleta
    -0.27
     desperately
    -0.26
    าหลี
    -0.26
    -0.25
     opinión
    -0.25
    POSITIVE LOGITS
     teasing
    0.77
     tease
    0.69
     prank
    0.68
     pranks
    0.66
     joke
    0.65
     mischie
    0.65
     laugh
    0.63
     joking
    0.61
     teased
    0.60
     mocking
    0.60
    Activations Density 0.225%

    No Known Activations