© 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. 109877
    Prev
    Next
    INDEX
    Explanations

    key terms related to client-server interactions and API requests

    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
     betweenstory
    -0.62
    WithIOException
    -0.62
    ChildScrollView
    -0.62
    queryInterface
    -0.60
     JpaRepository
    -0.60
    LLocation
    -0.58
    featureID
    -0.56
     Goa
    -0.55
    clover
    -0.54
    Clik
    -0.53
    POSITIVE LOGITS
     transfieras
    0.46
     newBuilder
    0.41
     Rücks
    0.38
     encaje
    0.35
    pecabe
    0.35
     novios
    0.35
     menudo
    0.34
     çar
    0.34
    queles
    0.34
    SharedCtor
    0.34
    Activations Density 0.164%

    No Known Activations