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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 9149
    Prev
    Next
    INDEX
    Explanations

    phrases related to safety and emergency preparedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.38
     Numerade
    -0.30
    transparent
    -0.29
    atase
    -0.27
     fresco
    -0.26
     clô
    -0.25
     carousel
    -0.25
    hexane
    -0.25
     surfaces
    -0.24
     translucent
    -0.23
    POSITIVE LOGITS
     emergency
    1.20
     Emergency
    1.05
    Emergency
    1.04
     emergencies
    1.00
    emergency
    1.00
     preparedness
    0.96
     EMERGENCY
    0.95
    EMERGENCY
    0.87
     Preparedness
    0.84
     disaster
    0.83
    Activations Density 0.613%

    No Known Activations