© 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. 23391
    Prev
    Next
    INDEX
    Explanations

    instances of the word "accurately."

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

    accurately portray, represent, detect, account, assess

    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
    Diwedd
    -0.46
    scriptcase
    -0.46
     EconPapers
    -0.44
     nakalista
    -0.44
     casera
    -0.43
    انجليز
    -0.42
     Paglinawan
    -0.41
     aikaa
    -0.41
    tinyos
    -0.40
     tekem
    -0.39
    POSITIVE LOGITS
     accurately
    1.47
     correctly
    1.14
     efficiently
    1.04
    correctly
    1.02
     reliably
    0.97
     correctement
    0.95
     properly
    0.94
     adequately
    0.93
     successfully
    0.89
    properly
    0.86
    Activations Density 0.017%

    No Known Activations