© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 15460
    Prev
    Next
    INDEX
    Explanations

    significant changes or variations in data measurements

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

    [Change/drop/rise/fall/increase/decrease] in something

    np_acts-logits-general · gemini-2.0-flash

    change in values

    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
    +#+#
    -0.70
    AndEndTag
    -0.55
    IContainer
    -0.53
     disambiguazione
    -0.53
    serviceWorker
    -0.49
    LookAnd
    -0.48
     henvisninger
    -0.47
    extAlignment
    -0.46
    uxxxx
    -0.46
     Pan
    -0.46
    POSITIVE LOGITS
     occurred
    0.68
     occurring
    0.62
     in
    0.60
     occurs
    0.60
     دریافت‌شده
    0.58
     caused
    0.55
    aktur
    0.55
     irmã
    0.54
     occasioned
    0.53
     avven
    0.53
    Activations Density 0.503%

    No Known Activations