© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5764
    Prev
    Next
    INDEX
    Explanations

    references to dishonesty and deception

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Mu
    -0.63
    ClientSize
    -0.61
     A
    -0.56
    帖最后由
    -0.56
     “
    -0.54
    ↵↵
    -0.54
     massimo
    -0.53
     a
    -0.51
     Gra
    -0.51
    Mu
    -0.50
    POSITIVE LOGITS
     lie
    1.45
     liar
    1.45
     Lying
    1.41
     lies
    1.36
     lied
    1.34
     LIE
    1.33
     lying
    1.31
     liars
    1.30
     Liar
    1.26
    Lies
    1.23
    Activations Density 0.194%

    No Known Activations