© 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. 27-GEMMASCOPE-RES-16K
    11. 10004
    Prev
    Next
    INDEX
    Explanations

    medical terms and actions related to health and safety measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nahilalakip
    -0.54
     hybridization
    -0.44
     disfr
    -0.43
    PREVIEW
    -0.43
     AssemblyCulture
    -0.41
    ParallelGroup
    -0.40
     annual
    -0.40
    givings
    -0.39
     الحره
    -0.39
     blooming
    -0.39
    POSITIVE LOGITS
     immediately
    0.97
     immediate
    0.87
    immediately
    0.80
     imediatamente
    0.79
     Immediately
    0.78
    Immediately
    0.77
    immediate
    0.75
     promptly
    0.75
    Immediate
    0.72
     emergency
    0.71
    Activations Density 0.592%

    No Known Activations