© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 110699
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "pare" and its variations within the context of medical and nutritional 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
     pare
    -2.41
    Pare
    -2.20
     Pare
    -2.08
    pare
    -2.08
    PARE
    -1.33
    pared
    -1.05
     paren
    -1.02
     Pareto
    -0.98
     pares
    -0.95
    paren
    -0.94
    POSITIVE LOGITS
    ResumeLayout
    0.44
     sienta
    0.38
     Njema
    0.35
     démon
    0.35
    antaranya
    0.35
    statechange
    0.33
     Komponenten
    0.32
     njego
    0.32
     seasonal
    0.32
     merciless
    0.31
    Activations Density 0.002%

    No Known Activations