© 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. 15428
    Prev
    Next
    INDEX
    Explanations

    references to software frameworks and collaborative projects in computing

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

    High energy physics collaborations and experiments

    np_acts-logits-general · gemini-2.0-flash

    particle physics collider experiments

    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
     '\\;'
    -0.69
    
    -0.60
    __*/
    -0.58
     PropertyChanged
    -0.56
    CompilerServices
    -0.55
    tvguidetime
    -0.54
    tible
    -0.54
    toMatch
    -0.54
    Geplaatst
    -0.52
    squareup
    -0.52
    POSITIVE LOGITS
     CERN
    0.55
     scintill
    0.54
     muon
    0.54
     ATLAS
    0.51
    EventLoop
    0.50
    ROOT
    0.49
    ModelAdmin
    0.49
     TPC
    0.48
     Collaboration
    0.48
     fisica
    0.48
    Activations Density 0.674%

    No Known Activations