© 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. 15927
    Prev
    Next
    INDEX
    Explanations

    elements of code related to software licensing and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     تضيفلها
    -0.52
    <?
    -0.45
     تكبرها
    -0.44
    wpi
    -0.38
     TextAppearance
    -0.38
    المناصب
    -0.33
    hradun
    -0.33
    ianum
    -0.33
    gameserver
    -0.32
    xase
    -0.32
    POSITIVE LOGITS
    SourceChecksum
    0.84
     autorytatywna
    0.65
     resourceCulture
    0.57
     desmotivaciones
    0.57
    AsUp
    0.54
    PreferredItem
    0.53
    kijken
    0.52
    expandindo
    0.52
    orologio
    0.48
    Modific
    0.45
    Activations Density 2.155%

    No Known Activations