© 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. 8116
    Prev
    Next
    INDEX
    Explanations

    technical terms and data related to cancer research

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

    Numbers "2" followed by another number, often "0-3"

    np_acts-logits-general · gemini-2.0-flash

    number 2

    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
    1
    -0.77
    ₁(
    -0.61
    １
    -0.60
     ১
    -0.59
     Eleventh
    -0.59
    ₁
    -0.58
     १
    -0.58
     eleventh
    -0.56
     WWI
    -0.55
    𝟷
    -0.54
    POSITIVE LOGITS
    2
    0.72
     يتيمه
    0.65
    Xna
    0.65
    CodedInputStream
    0.61
     متعلقه
    0.61
    InSection
    0.58
    tagext
    0.57
     مرئيه
    0.55
     ২
    0.55
    ২
    0.55
    Activations Density 0.527%

    No Known Activations