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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110532
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to significant figures in inventions and business

    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
     Kraft
    -2.09
    Kraft
    -1.96
     kraft
    -1.54
    kraft
    -1.53
     craft
    -0.82
    craft
    -0.81
    RAFT
    -0.79
     Craft
    -0.78
    Craft
    -0.74
     kracht
    -0.73
    POSITIVE LOGITS
    tagHelperRunner
    0.52
    enderror
    0.47
    routeProvider
    0.46
    Билгалдахарш
    0.45
     TType
    0.44
     GreatSchools
    0.44
     AppColors
    0.42
     ſhould
    0.41
     invol
    0.41
    httphttps
    0.41
    Activations Density 0.000%

    No Known Activations