© 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. 109067
    Prev
    Next
    INDEX
    Explanations

    phrases indicating an increase, addition, or emphasis on something

    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
     للاسماء
    -0.82
    :✨
    -0.79
    aarrggbb
    -0.73
    TagMode
    -0.71
     <=",
    -0.69
     esternos
    -0.65
    gnore
    -0.64
    endphp
    -0.63
     виправивши
    -0.63
     חיצוניים
    -0.62
    POSITIVE LOGITS
     yoktur
    0.41
    yelidikan
    0.34
    interprétation
    0.33
     emergencia
    0.31
     reproducción
    0.31
     Stimmung
    0.30
     guerras
    0.30
     pove
    0.30
    gantung
    0.30
     falsos
    0.30
    Activations Density 0.003%

    No Known Activations