© 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. 109868
    Prev
    Next
    INDEX
    Explanations

    instances of the word "bloody."

    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
     bloody
    -1.76
    bloody
    -1.56
     Bloody
    -1.56
    Bloody
    -1.45
     bloodshed
    -0.84
     blo
    -0.79
     bleeding
    -0.78
     blood
    -0.75
     bleed
    -0.75
     Blood
    -0.73
    POSITIVE LOGITS
    abetes
    0.52
     snippetHide
    0.52
    findpost
    0.46
     surla
    0.46
    RTLR
    0.46
    SharedCtor
    0.45
    Tembelea
    0.45
    ombus
    0.43
     للاسماء
    0.43
     propOrder
    0.43
    Activations Density 0.001%

    No Known Activations