Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109417
    Prev
    Next
    INDEX
    Explanations

    phrases that quantify or ask about amounts or quantities

    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
     much
    -0.96
    Much
    -0.88
    much
    -0.88
     Much
    -0.80
     mucho
    -0.70
     MUCH
    -0.64
     muchísimo
    -0.58
    mucho
    -0.56
     mycket
    -0.53
     paljon
    -0.50
    POSITIVE LOGITS
     initComponents
    0.54
     Paglinawan
    0.50
    AccessorTable
    0.49
     ivelany
    0.49
    findpost
    0.47
     createSlice
    0.45
     désolés
    0.45
    RUnlock
    0.44
     AssemblyTitle
    0.43
    :✨
    0.43
    Activations Density 0.004%

    No Known Activations