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. 109825
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating speed or rapidity

    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
     quickly
    -0.82
    Quickly
    -0.70
    quickly
    -0.70
     Quickly
    -0.68
     rapidly
    -0.66
     swiftly
    -0.63
     rápidamente
    -0.62
     быстро
    -0.59
     szybko
    -0.57
     rapidement
    -0.54
    POSITIVE LOGITS
    +#+#
    0.72
     nahilalakip
    0.63
     kysy
    0.53
     Taktlose
    0.51
     autorytatywna
    0.51
    exitRule
    0.51
    Diwedd
    0.51
     diſt
    0.51
     ſtand
    0.50
    Referanser
    0.50
    Activations Density 0.001%

    No Known Activations