© 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. 12888
    Prev
    Next
    INDEX
    Explanations

    complex expressions related to programming constructs and data structure definitions

    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
    RegressionTest
    -0.42
    TagMode
    -0.37
    AutoModerator
    -0.28
    UserScript
    -0.25
    FunctionFlags
    -0.24
    ]=>
    -0.23
    contentLoaded
    -0.22
     Numerade
    -0.21
    โ
    -0.20
    therefore
    -0.20
    POSITIVE LOGITS
    RenderAtEndOf
    0.81
     дописавши
    0.72
     يتيمه
    0.71
    Datuak
    0.66
    ьаж
    0.63
     ProtoMessage
    0.63
     disambiguazione
    0.63
     estekak
    0.62
    isContained
    0.61
    ScopeManager
    0.60
    Activations Density 1.011%

    No Known Activations