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 - 16k
    5. 22-GEMMASCOPE-MLP-16K
    6. 15853
    Prev
    Next
    INDEX
    Explanations

    references to medical institutions or terminology concerning blood glucose monitoring and diabetes management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijani
    -0.82
    ыгана
    -0.69
     SEDS
    -0.67
     समीक्षक
    -0.65
     Flock
    -0.65
     Савезне
    -0.64
     himo
    -0.63
    Tembelea
    -0.63
    ̍t
    -0.60
    newswire
    -0.60
    POSITIVE LOGITS
     őket
    0.62
    عاية
    0.52
     tryck
    0.48
     ihop
    0.48
    ">:
    0.46
    Oooh
    0.45
    yAxis
    0.45
     näm
    0.44
     professionnelle
    0.44
     visitare
    0.44
    Activations Density 0.673%

    No Known Activations