© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 9111
    Prev
    Next
    INDEX
    Explanations

    instances of lying or dishonesty

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ụn
    -0.46
    Zunanje
    -0.43
    </tfoot>
    -0.43
     كورة
    -0.42
    /**
    -0.41
    CodeAttribute
    -0.41
    ourge
    -0.39
    AnchorStyles
    -0.37
    ebrow
    -0.37
    mola
    -0.36
    POSITIVE LOGITS
     lied
    0.92
     mentiras
    0.88
     lies
    0.82
     Lying
    0.78
     lying
    0.77
     truthful
    0.75
     honesty
    0.74
     truth
    0.74
     mentira
    0.73
     lie
    0.72
    Activations Density 0.551%

    No Known Activations