© 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. 9-GEMMASCOPE-RES-16K
    11. 11058
    Prev
    Next
    INDEX
    Explanations

    references to deception and lying

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     provo
    -0.41
     Provost
    -0.35
     durian
    -0.33
     Cooley
    -0.32
    ctp
    -0.32
    require
    -0.31
     ready
    -0.31
     Happen
    -0.31
    conven
    -0.30
     prescribing
    -0.30
    POSITIVE LOGITS
     lied
    1.13
     lies
    1.10
     Lying
    1.09
     lie
    1.08
     lying
    1.07
     mentira
    1.06
     mentiras
    1.03
     Lies
    1.02
    Lying
    1.02
     liar
    0.95
    Activations Density 0.340%

    No Known Activations