© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 9-GEMMASCOPE-RES-131K
    6. 19873
    Prev
    Next
    INDEX
    Explanations

    the word "so" in various contexts, indicating an emphasis or amplification in the text

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

    .so file extensions

    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
     elástica
    -0.60
     mobiliario
    -0.54
     reciclaje
    -0.48
    avigation
    -0.47
    BeginContext
    -0.47
    iastical
    -0.46
     Neighbourhood
    -0.46
    trás
    -0.46
    lammatory
    -0.46
    pendicular
    -0.46
    POSITIVE LOGITS
    so
    2.28
    SO
    1.77
    So
    1.70
     So
    1.55
     SO
    1.53
     so
    1.49
    ソ
    1.16
    soa
    1.09
    soi
    1.05
    aso
    1.02
    Activations Density 0.024%

    No Known Activations