© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 14675
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to medical or scientific processes

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

    Followed by a comma or period

    np_acts-logits-general · gemini-2.0-flash

    concluding with therefore or otherwise

    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
     goddamn
    -0.89
     fuckin
    -0.88
     idéia
    -0.84
     mierda
    -0.74
     tranny
    -0.72
     fucked
    -0.70
     shitty
    -0.67
    fucking
    -0.67
     stupid
    -0.66
     Daß
    -0.66
    POSITIVE LOGITS
     https
    0.88
    . 
    0.87
    https
    0.83
     impactful
    0.79
    ttps
    0.77
     constexpr
    0.76
     ⁠
    0.76
     impacting
    0.74
     impacted
    0.73
     COVID
    0.72
    Activations Density 0.161%

    No Known Activations