© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 109377
    Prev
    Next
    INDEX
    Explanations

    repetitive use of the word "either."

    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
    Either
    -0.92
     Either
    -0.89
     either
    -0.87
    either
    -0.79
     entweder
    -0.65
    :+:
    -0.64
    
    -0.60
    Personendaten
    -0.52
    ITHER
    -0.50
     Soit
    -0.49
    POSITIVE LOGITS
    paramref
    0.36
     Autorizaciones
    0.36
     transfieras
    0.34
    的話
    0.33
    KommentareTeilen
    0.33
    翻攝
    0.33
     sumpay
    0.32
     חיצוניים
    0.31
    repr
    0.31
     jPanel
    0.31
    Activations Density 0.007%

    No Known Activations