© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 3360
    Prev
    Next
    INDEX
    Explanations

    references to meals and evening events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelAndView
    -0.62
     continúas
    -0.61
    WindowConstants
    -0.60
     contemporain
    -0.60
     contemporaine
    -0.59
     niitä
    -0.58
    iços
    -0.57
    zös
    -0.56
    первых
    -0.56
     Combustion
    -0.56
    POSITIVE LOGITS
     hour
    1.26
     Hour
    1.23
    Hour
    1.19
     HOUR
    1.10
    hour
    1.05
     evening
    0.98
     Mile
    0.95
    HOUR
    0.89
     mile
    0.87
     hours
    0.85
    Activations Density 0.065%

    No Known Activations