© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 10912
    Prev
    Next
    INDEX
    Explanations

    terms related to risk and danger

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     geldig
    -0.53
    PyTuple
    -0.49
    gezogen
    -0.47
     بيها
    -0.46
    RoutingModule
    -0.46
    umbler
    -0.45
     usati
    -0.44
     tà
    -0.43
     {}));
    -0.43
     mẽ
    -0.43
    POSITIVE LOGITS
     risk
    4.13
    risk
    3.66
     Risk
    3.61
     risks
    3.61
    Risk
    3.48
     RISK
    3.33
     Risks
    3.06
     riesgo
    2.97
    RISK
    2.95
    risks
    2.94
    Activations Density 0.074%

    No Known Activations