© 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. 5827
    Prev
    Next
    INDEX
    Explanations

    references to specific biological substances or conditions

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

    starting with "Nit", "Vit", "Rit", or "Pit"

    np_acts-logits-general · gemini-2.0-flash

    Ritonavir, Rittenberg, Pitot, nitros

    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
    er
    -0.81
    ه
    -0.81
     שוליים
    -0.80
    هما
    -0.76
    Hentet
    -0.69
    schule
    -0.60
    diğim
    -0.60
    erequisite
    -0.60
    diğimiz
    -0.58
    ed
    -0.58
    POSITIVE LOGITS
    ting
    0.83
     unknownFields
    0.74
    tingly
    0.69
    einander
    0.67
     SIT
    0.62
     Chit
    0.60
     Aitken
    0.59
    ters
    0.59
     PIT
    0.58
     Trit
    0.57
    Activations Density 0.381%

    No Known Activations