© 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. 1168
    Prev
    Next
    INDEX
    Explanations

    terms related to medical conditions or diagnoses

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

    Text after uncommon words

    np_acts-logits-general · gemini-2.0-flash

    scientific findings and medical treatment

    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
     which
    -0.73
     such
    -0.66
     Additionally
    -0.63
    Additionally
    -0.62
     either
    -0.61
     aforementioned
    -0.60
     puisque
    -0.57
     proprement
    -0.57
    hichever
    -0.56
     puisqu
    -0.56
    POSITIVE LOGITS
     :
    0.81
     autorytatywna
    0.76
    WithIOException
    0.73
    ?:
    0.71
     revisited
    0.69
     Meksiku
    0.63
     kaarangay
    0.63
    "].
    0.62
    : 
    0.62
    "،
    0.61
    Activations Density 0.778%

    No Known Activations