© 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. 28532
    Prev
    Next
    INDEX
    Explanations

    references to universities, particularly the University of Texas and its associated campuses

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

    university of texas

    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
    ThroughAttribute
    -0.47
    writerow
    -0.46
     humo
    -0.43
     linkovi
    -0.41
     vė
    -0.41
     įsi
    -0.41
     incendios
    -0.39
    scriptcase
    -0.38
     cálido
    -0.38
     sombras
    -0.36
    POSITIVE LOGITS
     Texas
    1.02
    Texas
    0.90
     texas
    0.85
    TEXAS
    0.79
    texas
    0.79
     TEXAS
    0.79
    GEBURTSDATUM
    0.69
     Texans
    0.68
     Texan
    0.65
     UT
    0.62
    Activations Density 0.004%

    No Known Activations