© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109371
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical values and their contextual usage

    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
    vielen
    -0.36
    irvana
    -0.30
     Einfach
    -0.27
    links
    -0.27
     einfach
    -0.27
     soil
    -0.25
     musiciens
    -0.25
     tablas
    -0.25
    мб
    -0.24
    insee
    -0.24
    POSITIVE LOGITS
    httphttps
    0.79
    rungsseite
    0.75
    sizeCache
    0.69
    AccessorTable
    0.63
    WebServlet
    0.62
    ########.
    0.60
    
    0.60
     Taktlose
    0.59
     kasarigan
    0.57
     disambiguazione
    0.57
    Activations Density 0.003%

    No Known Activations