© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 7639
    Prev
    Next
    INDEX
    Explanations

    instances of strategy, tactics, and deceptive behavior

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalTable
    -0.79
    lably
    -0.57
     nakalista
    -0.54
     Mandatory
    -0.54
    ="@+
    -0.54
    fordert
    -0.53
    antaine
    -0.53
    ViewFeatures
    -0.53
    énération
    -0.52
    readme
    -0.52
    POSITIVE LOGITS
     strategy
    1.84
     tactics
    1.79
     strategies
    1.73
    strategy
    1.67
     tactic
    1.64
     Strategy
    1.64
    strategies
    1.58
     strateg
    1.57
     Strategies
    1.56
     strategi
    1.54
    Activations Density 0.515%

    No Known Activations