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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 431
    Prev
    Next
    INDEX
    Explanations

    instances of irony or hypocrisy in statements or situations

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

    irony or hypocrisy

    np_acts-logits-general · gemini-2.0-flash

    irony and hypocrisy

    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
    PRNewswire
    -0.42
     nakalista
    -0.42
    reurs
    -0.36
     shared
    -0.34
    arangay
    -0.34
     版
    -0.33
    uced
    -0.33
     cond
    -0.33
     télécharge
    -0.33
    reur
    -0.32
    POSITIVE LOGITS
     irony
    0.75
     ironically
    0.68
     ironic
    0.66
    ironically
    0.63
    GTCX
    0.57
     Ironically
    0.56
    EndGlobalSection
    0.55
    Ironically
    0.54
    parsedMessage
    0.54
    windowFixed
    0.51
    Activations Density 0.399%

    No Known Activations