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. 109672
    Prev
    Next
    INDEX
    Explanations

    specific product names and features related to athletic apparel

    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
     verden
    -0.27
     mxArray
    -0.26
     tork
    -0.25
    ration
    -0.25
     lack
    -0.25
     color
    -0.24
    resultMap
    -0.24
     contributions
    -0.24
     erhält
    -0.23
     lauk
    -0.23
    POSITIVE LOGITS
    oa̍t
    0.72
    ulemon
    0.71
    IContainer
    0.68
    SharedDtor
    0.66
    verifyException
    0.66
     autorytatywna
    0.66
    AddTagHelper
    0.61
    Autoritní
    0.60
    RegressionTest
    0.59
     CURIAM
    0.59
    Activations Density 0.111%

    No Known Activations