© 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. 5668
    Prev
    Next
    INDEX
    Explanations

    delimiter or separators in text

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

    technical or web-related jargon and URLs.

    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
    balleur
    -0.57
    存于互联网档案馆
    -0.52
    Fly
    -0.52
     Pax
    -0.51
     Fly
    -0.51
    _
    
    -0.50
    Pax
    -0.50
    `
    
    -0.50
     ligiloj
    -0.49
    |
    
    -0.49
    POSITIVE LOGITS
    ooooo
    0.77
    oooooo
    0.67
    -----
    0.67
     =====
    0.66
    oooo
    0.65
    !!!!!
    0.65
    uxxxx
    0.65
    ------
    0.65
    !!!!
    0.64
    -------
    0.64
    Activations Density 0.381%

    No Known Activations