© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 27-GEMMASCOPE-RES-16K
    11. 7698
    Prev
    Next
    INDEX
    Explanations

    sentiments expressing irony and criticism

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GeoNames
    -0.37
    ெ
    -0.36
     Cooper
    -0.36
     mass
    -0.34
     slow
    -0.33
     solid
    -0.33
    ok
    -0.33
    堅
    -0.33
     Hunt
    -0.33
    我相信
    -0.32
    POSITIVE LOGITS
     irony
    1.88
     ironically
    1.80
     ironic
    1.71
     Ironically
    1.59
    Ironically
    1.52
    ironically
    1.42
     parado
    1.38
     paradox
    1.34
     paradoxical
    1.30
     oddly
    1.02
    Activations Density 0.459%

    No Known Activations