© 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. 108912
    Prev
    Next
    INDEX
    Explanations

    terms related to burdens and constraints, particularly in a contextual or metaphorical sense

    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
     load
    -0.60
    MessageTagHelper
    -0.58
    EndContext
    -0.58
    NUMX
    -0.57
     resourceCulture
    -0.57
     loads
    -0.52
     burdens
    -0.52
     surla
    -0.51
     LOAD
    -0.51
    estacks
    -0.51
    POSITIVE LOGITS
     ddelweddau
    0.50
     olvido
    0.42
     olvides
    0.42
     Gegner
    0.41
     apoder
    0.41
     espesor
    0.39
     quiera
    0.39
     Longueur
    0.39
     delgada
    0.38
     razonable
    0.38
    Activations Density 0.010%

    No Known Activations