© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. MLP Out - 16k
    9. 19-GEMMASCOPE-MLP-16K
    11. 11923
    Prev
    Next
    INDEX
    Explanations

    symbols or indicators of statistical significance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_19/width_16k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_mlp_out
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frequent
    -0.79
     intermittent
    -0.78
     frequent
    -0.75
    Frequent
    -0.72
    frequent
    -0.71
     periodic
    -0.69
     breaks
    -0.68
     periodically
    -0.67
     frequency
    -0.64
     infrequent
    -0.64
    POSITIVE LOGITS
     resourceCulture
    0.61
     Dicapai
    0.59
    urlopen
    0.59
    pyplot
    0.58
    晚餐
    0.56
    ContentAsync
    0.55
    xymatrix
    0.54
     ostavi
    0.53
     satunya
    0.53
     evening
    0.53
    Activations Density 0.374%

    No Known Activations