© 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. 3-GEMMASCOPE-RES-16K
    11. 2916
    Prev
    Next
    INDEX
    Explanations

    terms associated with danger and risk

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autocorrelation
    -0.81
     Poverty
    -0.72
    poverty
    -0.67
     poverty
    -0.65
     synthase
    -0.64
    quisa
    -0.64
    Poverty
    -0.64
     throm
    -0.63
     Polity
    -0.62
     synap
    -0.61
    POSITIVE LOGITS
     dangerous
    2.12
    dangerous
    1.88
     Dangerous
    1.87
    Dangerous
    1.73
     harmful
    1.60
     risky
    1.55
     hazardous
    1.49
     deadly
    1.44
     treacherous
    1.40
     perilous
    1.38
    Activations Density 0.166%

    No Known Activations