© 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 EvalsExportsinterp-engineNEWAPI 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. 7163
    Prev
    Next
    INDEX
    Explanations

    numerical data and statistical values

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

    Numbers within bracketed expressions

    np_acts-logits-general · gemini-2.0-flash

    quad numbers

    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
    tagext
    -0.80
    StoryboardSegue
    -0.73
     cdti
    -0.68
    SpringBootTest
    -0.68
    évaluateur
    -0.66
     tartalomajánló
    -0.66
     مرئيه
    -0.63
    出版年
    -0.62
    MessageTagHelper
    -0.62
    EDEFAULT
    -0.61
    POSITIVE LOGITS
     Quad
    0.50
    ----</
    0.49
     West
    0.49
     Ste
    0.47
    RRect
    0.47
    kuuta
    0.47
     quad
    0.47
     hình
    0.46
    spel
    0.45
     圆
    0.45
    Activations Density 0.680%

    No Known Activations