Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120813
    Prev
    Next
    INDEX
    Explanations

    terms related to emergency medical equipment and procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Paglinawan
    -0.38
     perioden
    -0.36
     intptr
    -0.33
    đu
    -0.32
     estadía
    -0.32
    xtick
    -0.30
     cromado
    -0.30
    catchError
    -0.30
    GraphicsUnit
    -0.30
    enumerable
    -0.29
    POSITIVE LOGITS
     paramedics
    0.60
     ambulance
    0.60
     Ambulance
    0.59
     ambulances
    0.55
    wapV
    0.54
    StoryboardSegue
    0.53
    PMailer
    0.49
     stretcher
    0.48
     EMT
    0.48
    reportWebVitals
    0.48
    Activations Density 0.038%

    No Known Activations