© 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. 109543
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "who" and its variations

    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
     wh
    -2.31
     Wh
    -2.03
    Wh
    -2.00
    wh
    -1.91
     WH
    -1.39
    WH
    -1.28
     whit
    -1.00
     whi
    -0.96
     Whal
    -0.91
     whe
    -0.87
    POSITIVE LOGITS
    튿
    0.41
    Datuak
    0.39
    hyrchwyd
    0.38
    liceerd
    0.36
     Lightboxes
    0.36
     zijne
    0.36
     dezelve
    0.36
     woorden
    0.35
    culada
    0.35
    kamers
    0.33
    Activations Density 0.002%

    No Known Activations