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. 6-GEMMASCOPE-MLP-16K
    6. 57
    Prev
    Next
    INDEX
    Explanations

    instances of the word "this" and expressions indicating contrast or comparison

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    rungsseite
    -0.97
     defaultstate
    -0.77
    `;
    
    -0.74
    DockStyle
    -0.74
    `
    
    -0.71
    GeoNames
    -0.69
     Orrell
    -0.68
    énario
    -0.67
    脚注の使い方
    -0.66
    __":
    
    -0.66
    POSITIVE LOGITS
    resor
    0.57
     nhảy
    0.47
    ObjectModel
    0.47
    MouseAdapter
    0.44
     res
    0.44
    anskje
    0.44
     release
    0.44
    iella
    0.43
     sw
    0.43
    ppia
    0.43
    Activations Density 0.587%

    No Known Activations