© 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. 110694
    Prev
    Next
    INDEX
    Explanations

    specific cultural or contextual terms and phrases that connote emotion or personality traits

    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
     mistakes
    -0.48
     bung
    -0.46
     messes
    -0.45
     blunder
    -0.42
     wrong
    -0.42
     mistake
    -0.42
     bot
    -0.41
     mess
    -0.41
     mismanagement
    -0.39
     clumsy
    -0.39
    POSITIVE LOGITS
     CreateTagHelper
    0.86
    ьаж
    0.62
     فريبيس
    0.62
    DebuggerNonUser
    0.60
    ✨:
    0.60
     &___
    0.59
    +:+
    0.58
     betweenstory
    0.58
     تضيفلها
    0.58
     Савезне
    0.57
    Activations Density 0.061%

    No Known Activations