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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 10725
    Prev
    Next
    INDEX
    Explanations

    references to perceptions of danger or threats related to health and safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.43
    GOTREF
    -0.40
     ErrIntOverflow
    -0.40
     oprot
    -0.40
     uLocal
    -0.40
    setVerticalGroup
    -0.39
     Stuck
    -0.35
     Debates
    -0.35
    ########.
    -0.34
    ❋
    -0.34
    POSITIVE LOGITS
     danger
    2.72
     threat
    2.61
     threats
    2.31
     dangers
    2.28
    threat
    2.25
     Danger
    2.16
     dangerous
    2.16
     Threat
    2.14
    danger
    2.13
    Threat
    2.09
    Activations Density 0.643%

    No Known Activations