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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108526
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives related to size and intensity

    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
    bill
    -0.34
    LayoutPanel
    -0.33
    Bill
    -0.32
    poso
    -0.32
    punkt
    -0.32
    pr
    -0.32
     محاس
    -0.31
    bold
    -0.30
    zorg
    -0.30
    AntiForgeryToken
    -0.29
    POSITIVE LOGITS
    ⓧ
    0.68
    +#+#
    0.68
    EndInit
    0.64
    +#+
    0.62
    ✨:
    0.59
     يتيمه
    0.57
    
    0.57
    Personendaten
    0.56
    OGND
    0.56
     otomatig
    0.56
    Activations Density 0.004%

    No Known Activations