© 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. 5676
    Prev
    Next
    INDEX
    Explanations

    numerical data or values in a document

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

    "8" and numbers around 8

    np_acts-logits-general · gemini-2.0-flash

    eighth and digits

    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
    ⑤
    -0.51
    ⑥
    -0.50
     חיצוניים
    -0.48
    estu
    -0.48
     Junho
    -0.47
     five
    -0.47
    五
    -0.45
     Савезне
    -0.44
     május
    -0.43
    ৫
    -0.43
    POSITIVE LOGITS
     eighth
    0.92
     Eighth
    0.86
    8
    0.85
    SharedCtor
    0.81
     Eigh
    0.80
     ویکی‌پدی
    0.75
     Eight
    0.74
     VIII
    0.73
     surla
    0.71
    第八
    0.71
    Activations Density 0.404%

    No Known Activations