© 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. 10-GEMMASCOPE-RES-16K
    11. 14159
    Prev
    Next
    INDEX
    Explanations

    terms related to danger or harmful situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     كومونز
    -0.89
     gynhyrchwyd
    -0.87
     برانيه
    -0.86
     Walkover
    -0.79
    :✨
    -0.78
    ClientSize
    -0.78
    arschijnlijk
    -0.77
    mergeFrom
    -0.77
    Sapp
    -0.76
    ilesh
    -0.75
    POSITIVE LOGITS
     dangerous
    1.60
     danger
    1.52
    Dangerous
    1.42
     Dangerous
    1.42
     dangers
    1.40
    dangerous
    1.38
     Danger
    1.37
    Danger
    1.26
    danger
    1.24
     Dangers
    1.21
    Activations Density 0.138%

    No Known Activations