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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 109657
    Prev
    Next
    INDEX
    Explanations

    gerunds and actions that indicate ongoing processes

    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
     shedding
    -0.60
    seeking
    -0.60
     AssemblyTitle
    -0.60
    doing
    -0.60
    standing
    -0.60
    Seeking
    -0.59
    acting
    -0.59
    selling
    -0.59
    entering
    -0.59
    failing
    -0.59
    POSITIVE LOGITS
     innovate
    0.35
     seleccionados
    0.34
     universitarios
    0.32
    recated
    0.32
     plástica
    0.31
     transfieras
    0.31
     pinulongan
    0.31
    pozorn
    0.30
    ounted
    0.30
    附属
    0.30
    Activations Density 0.341%

    No Known Activations