© 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. 21-GEMMASCOPE-RES-16K
    11. 11982
    Prev
    Next
    INDEX
    Explanations

    terms related to breathing and respiratory experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    期刊论文
    -0.62
     rabat
    -0.52
     plagioclase
    -0.52
     surla
    -0.50
     Guildford
    -0.48
    ulx
    -0.48
    amar
    -0.46
     Paraná
    -0.46
    τει
    -0.46
    blon
    -0.46
    POSITIVE LOGITS
     breath
    2.28
     breathe
    2.27
     breathing
    2.14
     breathes
    1.98
     breaths
    1.97
     Breathe
    1.95
     Breath
    1.91
     breathed
    1.90
    breath
    1.88
     Breathing
    1.83
    Activations Density 0.208%

    No Known Activations