Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109793
    Prev
    Next
    INDEX
    Explanations

    terms related to culture and cultural practices

    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
    cultural
    -1.03
    culture
    -0.84
    Cultural
    -0.81
    Culture
    -0.76
     cultural
    -0.72
    ULTURAL
    -0.71
     CULTURAL
    -0.70
    ulture
    -0.69
     culture
    -0.68
    ultural
    -0.67
    POSITIVE LOGITS
    ANTLR
    0.56
    richTextPanel
    0.43
    caloosa
    0.43
    HideFlags
    0.42
     bağlantılar
    0.41
     Spa
    0.40
    rath
    0.40
     вида
    0.40
    HtmlAttribute
    0.40
    SequentialGroup
    0.40
    Activations Density 0.003%

    No Known Activations