© 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. 109505
    Prev
    Next
    INDEX
    Explanations

    phrases indicating focus and attention in discussions

    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
    期刊论文
    -0.30
    really
    -0.27
    pertino
    -0.27
    ny
    -0.24
     Asamblea
    -0.24
     practiced
    -0.24
     Economía
    -0.24
    genius
    -0.23
     aprobado
    -0.23
    compatible
    -0.23
    POSITIVE LOGITS
    ponses
    0.71
     propOrder
    0.70
     ligiloj
    0.66
    Derbyniad
    0.60
    AutoScaleMode
    0.60
    SequentialGroup
    0.59
    XmlAccessType
    0.58
    WriteTagHelper
    0.58
    keyColumn
    0.57
     linkovi
    0.56
    Activations Density 0.073%

    No Known Activations