© 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. 5461
    Prev
    Next
    INDEX
    Explanations

    structured sentence endings or punctuation marks

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

    technical details about business, technology, or financial processes.

    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
     facts
    -0.28
     simples
    -0.28
     fac
    -0.27
     revenues
    -0.27
     only
    -0.26
     realities
    -0.26
    OrFail
    -0.26
     chances
    -0.26
    loat
    -0.26
     Reson
    -0.25
    POSITIVE LOGITS
    transQ
    0.87
     surla
    0.79
    Personensuche
    0.78
    GEBURTSDATUM
    0.76
     disambiguazione
    0.75
     informée
    0.75
     kasarigan
    0.67
     AssemblyCompany
    0.66
    Autoritní
    0.65
     تضيفلها
    0.65
    Activations Density 0.316%

    No Known Activations