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. 109783
    Prev
    Next
    INDEX
    Explanations

    the verb "be" in various tenses and contexts

    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
    parsedMessage
    -0.58
    存于互联网档案馆
    -0.58
    
    -0.57
    OGND
    -0.56
     }{@
    -0.56
    TableAdapter
    -0.55
    yntaxException
    -0.55
    WebVitals
    -0.54
    CodeAttribute
    -0.53
    featureID
    -0.53
    POSITIVE LOGITS
     CreateTagHelper
    0.36
     Vermögen
    0.36
     rağmen
    0.31
    Ārējās
    0.30
     graciosas
    0.30
     Klage
    0.30
     Boden
    0.29
     mini
    0.29
     Mitteln
    0.29
     Aufenthalt
    0.28
    Activations Density 0.009%

    No Known Activations