© 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-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9822
    Prev
    Next
    INDEX
    Explanations

    the term "lie" in various contexts and forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bradbury
    -0.60
    ServletException
    -0.60
    DotNetBar
    -0.56
    setattr
    -0.54
     годом
    -0.54
     sprocket
    -0.54
     unstoppable
    -0.54
    وفق
    -0.54
    Портал
    -0.54
     gezogen
    -0.53
    POSITIVE LOGITS
     lie
    2.96
     lies
    2.89
     lying
    2.85
     Lying
    2.60
    Lying
    2.47
     Lies
    2.37
    Lies
    2.23
     Lie
    2.21
     LIE
    2.20
    Lie
    2.11
    Activations Density 0.099%

    No Known Activations