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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11627
    Prev
    Next
    INDEX
    Explanations

    expressions related to breathing and respiration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "breath" or "breathing"

    np_acts-logits-general · gemini-2.0-flash

    breath and breathing out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ainville
    -0.56
     rabat
    -0.54
     Klon
    -0.50
     Cassidy
    -0.50
     Selena
    -0.50
     Buren
    -0.50
     Vele
    -0.49
    awtextra
    -0.49
     disponibilités
    -0.49
    JsonInclude
    -0.49
    POSITIVE LOGITS
     breath
    1.28
     Breath
    1.26
     breaths
    1.26
    Breathing
    1.26
     breathing
    1.25
     Breathing
    1.24
     breathe
    1.24
     breathed
    1.21
    breath
    1.20
    Breath
    1.18
    Activations Density 0.152%

    No Known Activations