© 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. 11561
    Prev
    Next
    INDEX
    Explanations

    technical specifications or labels related to programming structures or code definitions

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

    Assembly register/memory access

    np_acts-logits-general · gemini-2.0-flash

    from bank

    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
    kde
    -0.45
    jvm
    -0.44
     Mond
    -0.42
    DNS
    -0.41
     Guil
    -0.41
     kons
    -0.41
     PSE
    -0.40
    WebElementEntity
    -0.40
     panelists
    -0.40
    Fech
    -0.39
    POSITIVE LOGITS
     zewnętrzne
    0.73
     bit
    0.71
     Slaves
    0.71
     mihi
    0.67
     register
    0.67
     pinulongan
    0.67
     Enable
    0.66
     perifer
    0.66
    InitVars
    0.66
     Registers
    0.66
    Activations Density 1.975%

    No Known Activations