© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1784
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to individuals and specific brands or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper names, particularly of people in professional or entrepreneurial contexts.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mystère
    -0.57
     doigt
    -0.54
     ainfi
    -0.51
     ordinateur
    -0.51
     endroit
    -0.50
    łby
    -0.50
     Edad
    -0.49
     âge
    -0.48
     escalier
    -0.46
     bénéficiaire
    -0.46
    POSITIVE LOGITS
    ou
    0.78
    au
    0.75
    oulou
    0.75
     Pouch
    0.73
     Couch
    0.70
    wau
    0.69
     Bour
    0.69
    oun
    0.69
     Coul
    0.69
     BOUR
    0.68
    Activations Density 0.372%

    No Known Activations