© 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. 20-GEMMASCOPE-RES-16K
    11. 864
    Prev
    Next
    INDEX
    Explanations

    quantifiable data related to conditions, treatments, and research outcomes

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

    statistical data or numerical measurements in scientific/technical text.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    medical terminology and statistical data related to health conditions, particularly headaches and research studies.

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

    quantitative, technical reporting in scientific/medical contexts, especially statements of rates, percentages, prevalence, treatments, and measured outcomes.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     residency
    -0.34
     strategy
    -0.34
    еремо
    -0.33
     Sitz
    -0.32
     numerical
    -0.32
     Sawyer
    -0.32
     Nid
    -0.31
     disciplinary
    -0.31
     sir
    -0.31
     Kirk
    -0.30
    POSITIVE LOGITS
    webElementGuid
    0.91
    AnimationsModule
    0.90
     autorytatywna
    0.72
     насељу
    0.70
     CreateTagHelper
    0.66
    tagHelperRunner
    0.65
     Roskov
    0.61
     فريبيس
    0.61
    RTDA
    0.60
     Lightboxes
    0.59
    Activations Density 0.555%

    No Known Activations