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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 109168
    Prev
    Next
    INDEX
    Explanations

    references to government ministers and their roles

    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
     minister
    -1.20
     ministers
    -0.84
    minister
    -0.72
     ministres
    -0.58
     minist
    -0.57
     ministry
    -0.52
     ministro
    -0.50
    minist
    -0.50
     ministre
    -0.49
     الوز
    -0.48
    POSITIVE LOGITS
    出版年
    0.67
     CreateTagHelper
    0.63
    RTEX
    0.60
    yarnpkg
    0.54
    RenderAtEndOf
    0.51
    exitRule
    0.50
    sizeCache
    0.49
     typelib
    0.49
     Wikimedijinoj
    0.49
     AssemblyProduct
    0.48
    Activations Density 0.002%

    No Known Activations