© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 107159
    Prev
    Next
    INDEX
    Explanations

    terms related to swelling or increase in size

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

    swelling and edema

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للمعارف
    -0.67
    casio
    -0.65
    webElementXpaths
    -0.61
     Signalez
    -0.61
     DbType
    -0.60
    libft
    -0.59
    wpi
    -0.57
     Meksiku
    -0.57
    tanleria
    -0.57
    dataIndex
    -0.56
    POSITIVE LOGITS
     swelling
    1.73
     Swelling
    1.61
     swell
    1.49
     swells
    1.30
     swelled
    1.22
    swell
    1.20
     swollen
    1.13
    wollen
    0.75
    welling
    0.67
    edema
    0.67
    Activations Density 0.006%

    No Known Activations