© 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. 11626
    Prev
    Next
    INDEX
    Explanations

    numbers, particularly those related to measurements or statistics

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

    The number "four" or related terms/symbols

    np_acts-logits-general · gemini-2.0-flash

    number four

    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
     Seven
    -0.74
     FetchType
    -0.70
    7
    -0.64
    
    -0.60
     VII
    -0.58
     seven
    -0.58
     SEVEN
    -0.57
    urlpatterns
    -0.56
    Seven
    -0.53
     seventy
    -0.53
    POSITIVE LOGITS
     fourth
    0.96
     keempat
    0.90
     four
    0.84
    4
    0.84
    ⁴
    0.80
     forties
    0.79
    fourth
    0.78
     cuatro
    0.77
    four
    0.75
     FOURTH
    0.74
    Activations Density 0.461%

    No Known Activations