© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109559
    Prev
    Next
    INDEX
    Explanations

    references to specific dimensions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     dimensions
    -1.69
     Dimensions
    -1.43
    dimensions
    -1.34
     dimension
    -1.25
    Dimensions
    -1.25
     dimensiones
    -1.22
     DIMENSIONS
    -1.15
     dimensi
    -1.13
     Dimension
    -1.12
     dimensión
    -1.05
    POSITIVE LOGITS
     للمعارف
    0.60
     الحره
    0.50
    __":
    0.50
    SharedCtor
    0.49
     dAtA
    0.47
    ScopeManager
    0.47
     لينك
    0.47
    تفصیلات
    0.47
    tagHelperRunner
    0.47
     AssemblyCompany
    0.47
    Activations Density 0.003%

    No Known Activations