© 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. 9373
    Prev
    Next
    INDEX
    Explanations

    words related to scientific advancements and research methods

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

    formatting elements in documents like section headings, legal citation formats, and numeric data.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered 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
    Географиясе
    -0.77
     ModelExpression
    -0.73
    #+#
    -0.73
    AndEndTag
    -0.72
    iſchen
    -0.67
     Geſch
    -0.66
    ніципалі
    -0.64
    󠁢
    -0.64
    iastes
    -0.63
    Diweddarwch
    -0.62
    POSITIVE LOGITS
      
    0.37
    
    0.33
                                   
    0.32
    ................
    0.31
     Companies
    0.29
     Tri
    0.29
     Bracken
    0.28
    ↵↵
    0.28
    Capítulo
    0.28
     Company
    0.28
    Activations Density 0.496%

    No Known Activations