© 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 - 65k
    9. 16-GEMMASCOPE-RES-65K
    11. 28716
    Prev
    Next
    INDEX
    Explanations

    instances and variations of the word "facts."

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

    discussing facts

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ագրություններ
    -0.94
    তথ্যসূত্র
    -0.79
    ırken
    -0.73
     externi
    -0.72
    inyin
    -0.70
     newBuilder
    -0.70
    WriteTagHelper
    -0.69
    STRUCTIONS
    -0.68
     Emulator
    -0.68
    Архівовано
    -0.68
    POSITIVE LOGITS
     facts
    1.31
     FACT
    1.13
     Facts
    1.12
    facts
    1.07
    FACT
    1.03
     FACTS
    1.03
     Fact
    1.02
     fact
    0.97
    Facts
    0.94
     factual
    0.90
    Activations Density 0.038%

    No Known Activations