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. 99
    Prev
    Next
    INDEX
    Explanations

    references to time or future events

    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
    RenderAtEndOf
    -0.79
     récente
    -0.64
    хьтан
    -0.63
    CloseOperation
    -0.59
     reciente
    -0.58
     recent
    -0.58
     rând
    -0.57
    protoimpl
    -0.56
    StackNavigator
    -0.55
    Recent
    -0.54
    POSITIVE LOGITS
    
    0.64
    ropia
    0.59
    Referencies
    0.56
    Галерея
    0.56
    romes
    0.55
    îtra
    0.54
     GenerationType
    0.52
     futur
    0.52
    vrij
    0.50
     initComponents
    0.50
    Activations Density 0.152%

    No Known Activations