© 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. 130
    Prev
    Next
    INDEX
    Explanations

    references to scientific authors and their publications

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

    scientific citations or references in a specific format

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

    list of initials

    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
    TagMode
    -0.89
    ⓧ
    -0.71
    UnifiedTopology
    -0.59
    Will
    -0.58
    TestTools
    -0.57
    CppMethod
    -0.56
     مرئيه
    -0.56
    borderFill
    -0.54
     ujednoznacz
    -0.53
    Portale
    -0.53
    POSITIVE LOGITS
    InstrumentedTest
    0.72
    awtextra
    0.67
    RectangleBorder
    0.65
    GenerationType
    0.60
     Shakspeare
    0.58
    下载附件
    0.57
     Fatima
    0.56
    ıldız
    0.55
     itſelf
    0.53
     Boswell
    0.52
    Activations Density 0.025%

    No Known Activations