© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14424
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to healthcare and medical studies

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

    medical research study details, particularly about healthcare workers, medical conditions, and statistical information.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi

    demographic and population characteristics in academic research studies.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    demographic or statistical descriptions of human populations in academic or technical texts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    phrases describing study populations and cohort characteristics in epidemiological or academic research (e.g., prevalence, participants, locations, and institutional settings).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     VizieR
    -0.44
    ➟
    -0.37
     lors
    -0.37
     during
    -0.36
    plusplus
    -0.36
     utafitiHapana
    -0.35
    supset
    -0.35
    藉
    -0.35
    fromDate
    -0.35
    noopener
    -0.35
    POSITIVE LOGITS
     in
    0.83
     בישראל
    0.82
     Suomessa
    0.78
     בארץ
    0.72
     locally
    0.68
    Locally
    0.67
    日本では
    0.65
    在中国
    0.63
     located
    0.62
     ở
    0.62
    Activations Density 1.391%

    No Known Activations