© 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. 14917
    Prev
    Next
    INDEX
    Explanations

    terms related to programming errors and exceptions

    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
    utilisons
    -0.47
     Masyarakat
    -0.39
     Apabila
    -0.39
    routeProvider
    -0.38
    extAlignment
    -0.38
    embatan
    -0.36
     nervioso
    -0.35
     colourful
    -0.35
     viſ
    -0.35
    explique
    -0.35
    POSITIVE LOGITS
    ConstraintMaker
    0.60
     Autorisations
    0.58
     '\\;'
    0.55
     Delay
    0.45
     defaultstate
    0.45
     rå
    0.44
    danno
    0.43
     Bourne
    0.43
     bullion
    0.43
     '{@
    0.42
    Activations Density 0.871%

    No Known Activations