© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 11471
    Prev
    Next
    INDEX
    Explanations

    terms related to respiratory health and diseases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    astéro
    -0.57
    WebServlet
    -0.56
     disambiguazione
    -0.55
    appelle
    -0.54
    moine
    -0.54
     Wyman
    -0.53
     Kellogg
    -0.52
    ritsar
    -0.51
    rosine
    -0.50
     Schot
    -0.49
    POSITIVE LOGITS
     breathing
    1.36
     Breathing
    1.33
    Breathing
    1.29
     breathed
    1.25
     breathe
    1.24
     lungs
    1.22
    breathing
    1.21
     breaths
    1.20
     Breathe
    1.15
     breath
    1.14
    Activations Density 0.540%

    No Known Activations