© 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. 16-GEMMASCOPE-RES-16K
    11. 8383
    Prev
    Next
    INDEX
    Explanations

    specific biochemical terms and components often related to genetics and molecular biology

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

    after short, uncommon prefixes

    np_acts-logits-general · gemini-2.0-flash

    brolucizumab, aflibercept, Albert Heim

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -1.12
    GEBURTSDATUM
    -1.06
    SourceChecksum
    -1.06
     nahilalakip
    -1.03
     kaarangay
    -1.02
    verwijspagina
    -0.99
    setVerticalGroup
    -0.98
     وتسجيلات
    -0.98
     <=",
    -0.97
    EDEFAULT
    -0.97
    POSITIVE LOGITS
     they
    0.52
     They
    0.51
     Come
    0.50
    They
    0.50
     so
    0.44
    ="{{
    0.43
    Exactly
    0.42
    Come
    0.41
     You
    0.41
    <eos>
    0.39
    Activations Density 0.529%

    No Known Activations