© 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. 5454
    Prev
    Next
    INDEX
    Explanations

    references to academic or scientific journals and publications

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

    publications or academic functions

    np_acts-logits-general · gemini-2.0-flash

    student publication

    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
     noDo
    -0.63
     lenker
    -0.62
    onViewCreated
    -0.60
    KURZBESCHREIBUNG
    -0.60
     描
    -0.59
     bağlantılar
    -0.59
    ConstraintMaker
    -0.58
     kasarigan
    -0.58
    getItemId
    -0.56
    stateProvider
    -0.55
    POSITIVE LOGITS
     magazine
    1.33
     newspaper
    1.25
     weekly
    1.22
     newsletter
    1.20
     journal
    1.17
     magazines
    1.16
     periodical
    1.15
     newspapers
    1.15
     monthly
    1.08
     publication
    1.08
    Activations Density 0.281%

    No Known Activations