© 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. 110418
    Prev
    Next
    INDEX
    Explanations

    geographic references and proper nouns related to locations

    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
     Signalez
    -0.45
    achusetts
    -0.44
    GEBURTSDATUM
    -0.42
    NameInMap
    -0.36
    otry
    -0.35
    ynos
    -0.35
    partic
    -0.34
     identificación
    -0.33
    InjectMocks
    -0.33
     espejo
    -0.32
    POSITIVE LOGITS
     >=",
    0.54
     propOrder
    0.50
     BeautifulSoup
    0.50
    Referencies
    0.48
     собой
    0.47
    richTextPanel
    0.46
    TemporalType
    0.46
     AssemblyCompany
    0.46
     Gallimard
    0.46
    LEGGI
    0.45
    Activations Density 0.029%

    No Known Activations