© 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. 110291
    Prev
    Next
    INDEX
    Explanations

    repeated use of the word "dalam" (meaning "in" or "within" in Indonesian)

    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
     dalam
    -1.13
     Dalam
    -1.05
    Dalam
    -0.94
    dalam
    -0.91
     trong
    -0.74
     ſind
    -0.65
    parsedMessage
    -0.61
     nahilalakip
    -0.60
    hyrchwyd
    -0.60
    within
    -0.60
    POSITIVE LOGITS
     initComponents
    0.38
     createState
    0.35
     EXTR
    0.34
    arrol
    0.31
     dawn
    0.30
     bibit
    0.30
    ništvo
    0.30
    ociação
    0.30
    queles
    0.29
     PRINCIPAL
    0.29
    Activations Density 0.000%

    No Known Activations