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. 109656
    Prev
    Next
    INDEX
    Explanations

    temporal adverbs indicating timing or order

    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
     nakalista
    -0.49
     ModelExpression
    -0.44
     AssemblyCulture
    -0.38
    Slf
    -0.37
    hanced
    -0.35
     ögon
    -0.35
    __':
    -0.34
     endforeach
    -0.34
    __':
    
    -0.34
    webElementXpaths
    -0.33
    POSITIVE LOGITS
     utafitiHapana
    0.49
    ReusableCell
    0.48
    :✨
    0.45
    guém
    0.44
    Cyfeiriadau
    0.44
    geslacht
    0.44
    ddots
    0.43
    httphttps
    0.42
    readAll
    0.42
    bgcolor
    0.41
    Activations Density 0.018%

    No Known Activations