© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 1854
    Prev
    Next
    INDEX
    Explanations

    instances of manipulation and deception in societal contexts

    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
     AssemblyProduct
    -0.69
    httphttps
    -0.60
    ніципалі
    -0.60
    addCriterion
    -0.57
    hyrchwyd
    -0.57
     lenker
    -0.57
    DotNetBar
    -0.56
     AssemblyTitle
    -0.56
    Personensuche
    -0.55
    RSpec
    -0.55
    POSITIVE LOGITS
     fooled
    1.34
     gul
    1.24
     deceived
    1.18
     unsuspecting
    1.11
     naive
    1.06
     fool
    1.05
     fools
    1.05
     tricked
    1.05
     foolish
    1.04
     fall
    1.02
    Activations Density 0.242%

    No Known Activations