© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13129
    Prev
    Next
    INDEX
    Explanations

    patterns related to data structure definitions and operations in programming

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

    Protobuf visitor methods

    np_acts-logits-general · gemini-2.0-flash

    variable field descriptors

    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
    ברית
    -0.44
    czerw
    -0.42
    lgica
    -0.41
    PLIED
    -0.41
    Singing
    -0.41
    IGraphics
    -0.40
    zzlies
    -0.40
     deswegen
    -0.40
    PORARY
    -0.40
    IFIED
    -0.39
    POSITIVE LOGITS
    tagext
    0.74
    UnusedPrivate
    0.72
    出版年
    0.71
    +#+#
    0.71
    HtmlAttribute
    0.71
     EClass
    0.71
     propOrder
    0.69
     houſe
    0.69
    IBOutlet
    0.66
    ItemBackground
    0.66
    Activations Density 1.929%

    No Known Activations