© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 12509
    Prev
    Next
    INDEX
    Explanations

    instances of deceit or dishonesty

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     виправивши
    -0.82
     isNameExpr
    -0.75
    autoreleasepool
    -0.67
     mouseY
    -0.63
     getchar
    -0.63
     >=",
    -0.63
     AssemblyProduct
    -0.63
    })));
    -0.63
     onResponse
    -0.60
     ModelExpression
    -0.60
    POSITIVE LOGITS
     lie
    1.84
     lies
    1.80
     falsehood
    1.59
     lied
    1.57
     Lies
    1.55
     mentira
    1.53
     lying
    1.48
     Lying
    1.45
     false
    1.45
     Lie
    1.41
    Activations Density 0.517%

    No Known Activations