© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3948
    Prev
    Next
    INDEX
    Explanations

    references to inventions and patents associated with various products

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

    Cutting or removing something

    np_acts-logits-general · gemini-2.0-flash

    cut-off shorts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     propOrder
    -0.77
    GraphicsUnit
    -0.76
     ویکی‌پدیا
    -0.70
    setViewportView
    -0.63
    PointerException
    -0.62
    DebuggerNonUser
    -0.61
    ⓧ
    -0.61
    HostException
    -0.61
    onViewCreated
    -0.61
     typelib
    -0.60
    POSITIVE LOGITS
     cutting
    1.65
     cut
    1.64
     cuts
    1.58
     Cuts
    1.48
     Cut
    1.47
     Cutting
    1.47
    Cutting
    1.42
    Cut
    1.40
    cut
    1.39
    Cuts
    1.39
    Activations Density 0.188%

    No Known Activations