© 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. 12339
    Prev
    Next
    INDEX
    Explanations

    phrases or terms related to structured data, programming, and mathematical concepts

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

    Code, dates, and other technical language

    np_acts-logits-general · gemini-2.0-flash

    surveys, Max, minify, ill, Tuesday, ratio, V

    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
     ویکی‌پدیا
    -0.91
    脚注の使い方
    -0.82
     autorytatywna
    -0.81
    PerformLayout
    -0.76
    ագրություններ
    -0.73
    Hozzáférés
    -0.72
     condamné
    -0.70
     enfans
    -0.70
    ReusableCell
    -0.69
    featureID
    -0.68
    POSITIVE LOGITS
    那一
    0.51
    _
    0.50
     module
    0.49
    protoimpl
    0.48
    -
    0.43
    ToolStrip
    0.43
     pom
    0.42
     el
    0.42
    XmlEnum
    0.42
    !
    0.41
    Activations Density 0.377%

    No Known Activations