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-2-2B
    4. MLP Out - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8836
    Prev
    Next
    INDEX
    Explanations

    references to vessels and maritime terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ти
    -0.50
    umenical
    -0.45
     achtergrond
    -0.43
    نين
    -0.43
    ắng
    -0.42
     cô
    -0.42
     urma
    -0.41
     acoper
    -0.40
     Hintergrund
    -0.40
    полнитель
    -0.40
    POSITIVE LOGITS
    TypedDataSet
    1.17
     незавершена
    1.16
    sizeCache
    0.96
     ModelExpression
    0.94
     ExecuteAsync
    0.90
    ThroughAttribute
    0.87
     Normdatei
    0.86
     चीज़ों
    0.86
    IContainer
    0.85
    principalColumn
    0.85
    Activations Density 1.144%

    No Known Activations