© 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. 20-GEMMASCOPE-RES-131K
    6. 54687
    Prev
    Next
    INDEX
    Explanations

    references to GPS technology or terminology

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

    GPS location and tracking

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     New
    -0.41
    <h2>
    -0.39
     middle
    -0.38
    ter
    -0.37
     Berk
    -0.37
     Whole
    -0.36
     strong
    -0.36
     Middle
    -0.36
     new
    -0.35
     different
    -0.35
    POSITIVE LOGITS
     GPS
    1.39
    GPS
    1.31
     gps
    1.29
    gps
    1.13
    Gps
    1.03
    gameserver
    0.83
    Autoritní
    0.79
    ſelf
    0.67
    Personensuche
    0.67
    LLocation
    0.66
    Activations Density 0.002%

    No Known Activations