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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 3702
    Prev
    Next
    INDEX
    Explanations

    references to lying or deceitful behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Décès
    -0.69
     рады
    -0.66
     Allentown
    -0.63
    évaluateur
    -0.63
     Câmara
    -0.62
    hadiran
    -0.61
     McIn
    -0.60
     antemano
    -0.59
    {\
    -0.59
     Maynard
    -0.59
    POSITIVE LOGITS
     lie
    2.43
     lies
    2.21
     lying
    2.06
     LIE
    2.00
     Lie
    1.93
     Lies
    1.82
     Lying
    1.80
    Lies
    1.79
    Lying
    1.74
    Lie
    1.70
    Activations Density 0.070%

    No Known Activations