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 - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 60993
    Prev
    Next
    INDEX
    Explanations

    references to the company "Pfizer."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Inc
    -1.14
    Inc
    -0.85
    UrlResolution
    -0.74
    tagHelperRunner
    -0.73
     архивлан
    -0.67
    }))
    
    -0.66
    PageRoute
    -0.65
    addPreferredGap
    -0.64
    Vidite
    -0.63
    ніципа
    -0.63
    POSITIVE LOGITS
     Monfieur
    0.85
     myſelf
    0.81
     Theſe
    0.75
     whoſe
    0.74
     Efq
    0.69
     fince
    0.69
     Jefus
    0.68
     photolibrary
    0.68
     sourire
    0.66
     itſelf
    0.66
    Activations Density 0.024%

    No Known Activations