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. 109786
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns indicating ownership or association

    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
     dezelve
    -0.66
     مرئيه
    -0.61
    antaranya
    -0.59
    +#+#
    -0.58
    harapkan
    -0.57
    orsese
    -0.57
    хьтан
    -0.56
    ckså
    -0.55
     Lingkungan
    -0.54
     Infór
    -0.52
    POSITIVE LOGITS
     cref
    0.47
    WebServlet
    0.43
    //
    0.38
     combineReducers
    0.38
    BuildContext
    0.37
    
    0.35
    KommentareTeilen
    0.35
     az
    0.34
     bar
    0.33
     Web
    0.33
    Activations Density 0.271%

    No Known Activations