© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 6212
    Prev
    Next
    INDEX
    Explanations

    technical jargon related to semiconductor devices and their properties

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

    Semiconductor physics and doping

    np_acts-logits-general · gemini-2.0-flash

    doped semiconductor band

    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
    BeginContext
    -0.62
     مفص
    -0.53
    setPointSize
    -0.49
    fjspx
    -0.48
    νώ
    -0.47
     урна
    -0.46
    的头
    -0.45
    头
    -0.45
    aterdag
    -0.45
    ########.
    -0.44
    POSITIVE LOGITS
     semiconductor
    0.73
     hole
    0.68
     carriers
    0.68
     conduction
    0.68
     band
    0.67
     doping
    0.67
     Semiconductor
    0.66
     semiconductors
    0.66
     drain
    0.65
     transistor
    0.64
    Activations Density 1.162%

    No Known Activations