© 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. 20-GEMMASCOPE-RES-16K
    11. 6990
    Prev
    Next
    INDEX
    Explanations

    instances of deception and pretense in interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    complex narrative descriptions involving undercover or disguised characters.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.50
     obispo
    -0.45
    horabuena
    -0.44
     campeones
    -0.44
    addCriterion
    -0.42
     fieles
    -0.42
    readFileSync
    -0.40
     Heraus
    -0.38
     énergé
    -0.38
     Hauses
    -0.37
    POSITIVE LOGITS
     pretending
    0.63
     pretend
    0.62
     pretended
    0.61
     feign
    0.57
     pretends
    0.56
     pseud
    0.56
     pretence
    0.56
     pretense
    0.56
     fake
    0.54
     propOrder
    0.53
    Activations Density 0.286%

    No Known Activations