© 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. 10487
    Prev
    Next
    INDEX
    Explanations

    elements related to GPU processing and CUDA architecture

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

    Software or library versions

    np_acts-logits-general · gemini-2.0-flash

    major version strings

    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
    roquia
    -0.49
    kkal
    -0.38
     tav
    -0.38
    บรร
    -0.38
    лях
    -0.37
    medim
    -0.35
    はじめに
    -0.35
    arashtra
    -0.35
    atguigu
    -0.35
    Enigma
    -0.34
    POSITIVE LOGITS
     version
    1.69
    version
    1.65
     versions
    1.61
    Version
    1.57
     Versions
    1.57
     Version
    1.50
     getVersion
    1.49
     VERSION
    1.49
    版本
    1.42
    VERSION
    1.40
    Activations Density 0.373%

    No Known Activations