© 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 - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 13279
    Prev
    Next
    INDEX
    Explanations

    instances of mocking or ridicule directed towards individuals or groups

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

    mocking or ridiculing someone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toxin
    -0.42
     poison
    -0.41
     nahilalakip
    -0.39
    sweetalert
    -0.38
     anti
    -0.38
     toxins
    -0.38
     Anti
    -0.36
     ama
    -0.36
     toxic
    -0.36
     mel
    -0.36
    POSITIVE LOGITS
     ridicule
    0.74
     jokes
    0.73
     ridiculed
    0.72
     joke
    0.71
     chistes
    0.66
    Jokes
    0.66
     mocked
    0.63
     autorytatywna
    0.62
     mockery
    0.61
     laughed
    0.60
    Activations Density 0.016%

    No Known Activations