© 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-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 4900
    Prev
    Next
    INDEX
    Explanations

    references to the act of breathing or breath-related expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 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
     autorytatywna
    -0.47
     pinulongan
    -0.45
     proszę
    -0.39
    Horst
    -0.38
     matrícula
    -0.38
     כולל
    -0.37
    ztály
    -0.37
    luit
    -0.36
     dimiliki
    -0.36
     culte
    -0.36
    POSITIVE LOGITS
     breath
    0.88
    boat
    0.78
    breath
    0.77
     boat
    0.74
     figured
    0.74
     figuring
    0.72
     Breath
    0.63
     BOAT
    0.62
     breathe
    0.61
     breathing
    0.60
    Activations Density 0.213%

    No Known Activations