© 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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8671
    Prev
    Next
    INDEX
    Explanations

    deceptive behavior and dishonesty in statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/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.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.39
    UIControlState
    -0.38
    ụn
    -0.37
    có
    -0.34
    </tfoot>
    -0.34
    demo
    -0.33
     presump
    -0.33
    Zunanje
    -0.33
    too
    -0.32
     Hohen
    -0.32
    POSITIVE LOGITS
     lied
    0.93
     mentiras
    0.84
     Lying
    0.81
     lying
    0.79
     lies
    0.77
     lie
    0.74
     Lies
    0.73
    谎
    0.73
     liar
    0.70
    Lying
    0.70
    Activations Density 0.417%

    No Known Activations