© 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
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110369
    Prev
    Next
    INDEX
    Explanations

    the word "まで," which indicates a limit or extent in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    まで
    -1.36
     まで
    -1.00
    까지
    -0.90
    までは
    -0.79
    までの
    -0.77
    までに
    -0.71
    までも
    -0.65
    until
    -0.56
     hasta
    -0.56
    tagHelperRunner
    -0.54
    POSITIVE LOGITS
    #
    0.50
    脚注の使い方
    0.46
    UnitTesting
    0.40
    /**
    0.40
    ありますか
    0.38
    ⓧ
    0.37
    nologue
    0.36
    laut
    0.35
    ところです
    0.35
    maxcdn
    0.35
    Activations Density 0.001%

    No Known Activations