© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3700
    Prev
    Next
    INDEX
    Explanations

    terms associated with scientific research and documentation

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

    starting with "atr" or "att"

    np_acts-logits-general · gemini-2.0-flash

    atrop/athy/satin/lattices/atri/ATTR/Atlas/atex

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    
    -0.64
     ſind
    -0.56
    awtextra
    -0.55
     désolés
    -0.53
    sizeCache
    -0.53
     '\\;'
    -0.53
    cleared
    -0.52
     Compos
    -0.52
    %)$
    -0.52
    Lik
    -0.50
    POSITIVE LOGITS
    at
    0.62
    ton
    0.60
    tt
    0.59
    titia
    0.57
     Atkinson
    0.56
     Matilda
    0.54
    tp
    0.53
    to
    0.53
     Bettina
    0.52
    ty
    0.52
    Activations Density 1.024%

    No Known Activations