© 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. 18-GEMMASCOPE-RES-16K
    11. 9883
    Prev
    Next
    INDEX
    Explanations

    statements asserting facts about various subjects

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

    "fact" or "the fact that"

    np_acts-logits-general · gemini-2.0-flash

    fact that

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awaiter
    -0.68
    ագրություններ
    -0.66
    ised
    -0.64
    RenderAtEndOf
    -0.62
    ̈́
    -0.61
     Catawiki
    -0.58
     SafeMath
    -0.57
    endpush
    -0.57
    interceptors
    -0.56
     externi
    -0.56
    POSITIVE LOGITS
     fact
    1.37
     Fact
    1.25
     FACT
    1.20
    fact
    1.19
    FACT
    1.07
    Fact
    1.04
     Facts
    0.92
     facts
    0.91
     Tatsache
    0.84
    facts
    0.83
    Activations Density 0.093%

    No Known Activations