© 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. 108617
    Prev
    Next
    INDEX
    Explanations

    the frequency of the word 'soon' as well as other words that indicate timing

    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
     soon
    -1.22
    Soon
    -1.04
     Soon
    -1.02
    soon
    -0.98
     SOON
    -0.94
     bientôt
    -0.78
     foon
    -0.67
     snart
    -0.64
     shortly
    -0.62
     sooner
    -0.53
    POSITIVE LOGITS
     jScrollPane
    0.57
     ویکی‌پدیا
    0.56
    oa̍t
    0.55
    ngdoc
    0.54
     تضيفلها
    0.54
     Perſ
    0.53
    Personendaten
    0.53
     ſind
    0.52
     autorytatywna
    0.51
    afficheront
    0.51
    Activations Density 0.002%

    No Known Activations