© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 6719
    Prev
    Next
    INDEX
    Explanations

    references to safety and protective measures in hazardous situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ญ
    -0.34
     Paglinawan
    -0.33
    apeake
    -0.33
    емость
    -0.33
    NonQuery
    -0.32
    บ้าง
    -0.30
     Root
    -0.30
    omitempty
    -0.30
    brtc
    -0.30
     nadzieję
    -0.29
    POSITIVE LOGITS
     المعيارى
    0.77
     dangerous
    0.73
     danger
    0.72
     hazard
    0.70
     hazardous
    0.67
    hazard
    0.67
    Danger
    0.67
     dangers
    0.64
    danger
    0.64
     dangereux
    0.64
    Activations Density 0.299%

    No Known Activations