© 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. 109026
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lies."

    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
     lie
    -1.02
     lies
    -0.90
     Lie
    -0.67
    Lie
    -0.66
     lying
    -0.63
    Lies
    -0.62
     liegen
    -0.57
     Lies
    -0.55
     Lying
    -0.54
     liegt
    -0.53
    POSITIVE LOGITS
     CreateTagHelper
    0.45
     disambiguazione
    0.42
    цезда
    0.39
    /**
    0.39
    ipheral
    0.38
    /*
    0.37
    AutoScaleMode
    0.37
    RenderAtEndOf
    0.36
     Utilizamos
    0.36
    Földrajzportál
    0.36
    Activations Density 0.003%

    No Known Activations