© 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. 108292
    Prev
    Next
    INDEX
    Explanations

    references to patents or patent-related concepts

    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
     pat
    -2.63
     Pat
    -1.89
    Pat
    -1.82
    pat
    -1.76
     PAT
    -1.27
    PAT
    -1.27
     patted
    -1.10
     pats
    -1.00
     patro
    -1.00
     Patt
    -0.98
    POSITIVE LOGITS
     kasarigan
    0.49
    eleste
    0.46
    ıklı
    0.45
    NameInMap
    0.42
    DockStyle
    0.42
    onOptions
    0.41
    ativement
    0.41
     wynika
    0.41
    aughter
    0.41
    🖨
    0.40
    Activations Density 0.001%

    No Known Activations