© 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. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13691
    Prev
    Next
    INDEX
    Explanations

    references to quantitative measurements and experimental conditions

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

    numerical expressions that represent time periods, especially those formatted as "X-year" or "X-fold" measurements.

    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
     Verhältnisse
    -0.55
     steder
    -0.54
     Geset
    -0.48
     peraturan
    -0.46
     comportement
    -0.44
     Regionen
    -0.44
     lisäksi
    -0.43
    queles
    -0.43
     gedrag
    -0.43
     grupper
    -0.43
    POSITIVE LOGITS
     faſt
    0.76
     ſte
    0.72
     quadri
    0.71
     multi
    0.70
     semi
    0.69
     multifaceted
    0.66
    postsleuth
    0.66
     unſ
    0.66
     flat
    0.66
     multicolor
    0.66
    Activations Density 0.233%

    No Known Activations