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. 6-GEMMASCOPE-MLP-16K
    6. 165
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions related to gauge theory and symmetry in physics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    تقاوى
    -0.71
     المعيارى
    -0.69
    osoba
    -0.65
    ########.
    -0.65
    expandindo
    -0.65
     BorderRadius
    -0.62
    انيف
    -0.61
     Extragalactic
    -0.60
     pinulongan
    -0.60
     ChromeDriver
    -0.59
    POSITIVE LOGITS
     ModelExpression
    0.61
    Fuß
    0.50
    PerformLayout
    0.49
    AutoSize
    0.49
    addCriterion
    0.48
    如何在
    0.46
    zám
    0.44
    wakili
    0.44
     légale
    0.44
     actuar
    0.42
    Activations Density 0.935%

    No Known Activations