© 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. 109882
    Prev
    Next
    INDEX
    Explanations

    references to Hamiltonians in physics, particularly those indicating interactions and properties in 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
    ⓧ
    -0.48
    ⓘ
    -0.43
    osexuality
    -0.43
    avigation
    -0.43
     Hivatalos
    -0.42
    曖昧さ回避
    -0.42
    ftances
    -0.39
    imantan
    -0.39
     utafitiHapana
    -0.39
     становника
    -0.39
    POSITIVE LOGITS
     مرئيه
    0.50
     ModelExpression
    0.47
    DockStyle
    0.46
    клопе
    0.44
    UnusedPrivate
    0.43
     informée
    0.43
     '\\;'
    0.42
     mergeFrom
    0.40
    MethodManager
    0.40
    principalTable
    0.39
    Activations Density 0.054%

    No Known Activations