© 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. 109036
    Prev
    Next
    INDEX
    Explanations

    technical specifications and measurements related to mechanical systems

    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
     engineering
    -0.42
     ENGINEER
    -0.36
     ingeniería
    -0.35
     Engineering
    -0.35
     ingenieros
    -0.34
     ENGINEERING
    -0.33
     engineer
    -0.32
     müh
    -0.32
    볍
    -0.31
    工程师
    -0.30
    POSITIVE LOGITS
    contentLoaded
    0.90
    parsedMessage
    0.80
    :✨
    0.78
    ंदीखरीदारी
    0.75
     ब्रेकडाउन
    0.74
    Personendaten
    0.73
    awtextra
    0.73
     autorytatywna
    0.69
    ScopeManager
    0.68
    RenderAtEndOf
    0.66
    Activations Density 0.132%

    No Known Activations