© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110195
    Prev
    Next
    INDEX
    Explanations

    terminology related to reproductive health and technologies

    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
     reproductive
    -1.57
     Reproductive
    -1.32
    Reproductive
    -1.21
     reproduction
    -1.05
     Reproduction
    -0.91
     reprodu
    -0.89
    Reproduction
    -0.86
     Reprodu
    -0.77
    Reprodu
    -0.71
     reproduce
    -0.71
    POSITIVE LOGITS
    parsedMessage
    0.71
     otomatig
    0.63
    WireFormatLite
    0.61
    featureID
    0.61
    DockStyle
    0.58
    findpost
    0.56
     Infór
    0.55
    ьаж
    0.55
     bezeichneter
    0.55
    AddTagHelper
    0.54
    Activations Density 0.006%

    No Known Activations