© 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. 16-GEMMASCOPE-RES-16K
    11. 13721
    Prev
    Next
    INDEX
    Explanations

    concepts related to health and medical research

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

    followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    relies on or leads to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    definitely
    -0.43
    WindowConstants
    -0.43
     dag
    -0.43
    <eos>
    -0.42
    ajs
    -0.42
    writerow
    -0.42
    ままで
    -0.41
     tur
    -0.41
     x
    -0.41
     Makes
    -0.41
    POSITIVE LOGITS
     relies
    0.78
     depends
    0.76
     presupposes
    0.73
     involves
    0.71
    之所以
    0.70
     незавершена
    0.69
     består
    0.68
     simply
    0.68
    simply
    0.68
    SCRIBE
    0.68
    Activations Density 0.787%

    No Known Activations