© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 182
    Prev
    Next
    INDEX
    Explanations

    programming-related structures and function definitions

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

    programming-related terms and constructs

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

    autorest, constructor, Appveyor CI

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    BeforeMethod
    -0.55
    uminense
    -0.48
     --
    -0.45
     наоборот
    -0.44
     پذ
    -0.43
    ManagedBean
    -0.43
     TestBed
    -0.43
     jTextField
    -0.43
    蚪
    -0.42
     pylint
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.80
     Chwiliwch
    0.77
     kasarigan
    0.75
    
    0.74
    DoubleQuotes
    0.73
     חיצוניים
    0.70
    )':
    0.69
    Билгалдахарш
    0.64
    :\/\/
    0.64
    SequentialGroup
    0.64
    Activations Density 0.113%

    No Known Activations