© 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. 110212
    Prev
    Next
    INDEX
    Explanations

    words relating to color descriptions

    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
     colored
    -2.11
     coloured
    -1.91
    colored
    -1.91
     Colored
    -1.83
    Colored
    -1.73
    coloured
    -1.67
     Coloured
    -1.66
     coloring
    -1.13
    coloring
    -1.09
     coloré
    -1.09
    POSITIVE LOGITS
     Travel
    0.32
     LCCN
    0.32
    Decrement
    0.31
     наоборот
    0.30
    Bienvenido
    0.30
     Laut
    0.30
     rokok
    0.30
    leps
    0.29
    super
    0.29
     travel
    0.29
    Activations Density 0.002%

    No Known Activations