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. 61014
    Prev
    Next
    INDEX
    Explanations

    the concept of "commonness" or widely recognized ideas and practices

    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
    common
    -1.46
    Common
    -0.89
     comunes
    -0.84
     connus
    -0.83
     común
    -0.82
     comum
    -0.82
     faciles
    -0.80
     mères
    -0.80
     courants
    -0.79
     complètes
    -0.77
    POSITIVE LOGITS
     Efq
    1.14
     myſelf
    1.03
     Conſ
    0.98
     Monfieur
    0.98
     Reſ
    0.96
     Eſ
    0.95
     Diſ
    0.95
    neſs
    0.92
     whoſe
    0.92
    ſelf
    0.91
    Activations Density 0.027%

    No Known Activations