© 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. 11803
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual or entity, likely named "Sur" or "Sur ratt."

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

    sur- words, Surratt, Surreptitiously

    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
     Keuangan
    -0.56
     maș
    -0.52
    otechnology
    -0.51
    oteo
    -0.51
     uș
    -0.51
     Kebijakan
    -0.50
    <h6>
    -0.50
     démocr
    -0.50
     Penga
    -0.49
     vectorielles
    -0.48
    POSITIVE LOGITS
     Sur
    2.22
    Sur
    2.17
     sur
    2.05
     SUR
    1.95
    sur
    1.94
    SUR
    1.70
     Surfer
    1.25
     surfactant
    1.13
     surf
    1.09
     Surf
    1.09
    Activations Density 0.010%

    No Known Activations