© 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. 22-GEMMASCOPE-RES-16K
    11. 5628
    Prev
    Next
    INDEX
    Explanations

    events related to specific moments or milestones in sports games

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

    Occurrences after articles or prepositions

    np_acts-logits-general · gemini-2.0-flash

    halftime and start

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RunAsync
    -0.55
    uxxxx
    -0.52
     seeded
    -0.50
     perdana
    -0.48
     germinate
    -0.47
     mace
    -0.46
    dists
    -0.46
     '\\;'
    -0.44
     possessive
    -0.44
     germin
    -0.43
    POSITIVE LOGITS
     halftime
    1.25
     half
    0.95
     break
    0.90
    Half
    0.85
     intermission
    0.84
     interval
    0.82
    ScopeManager
    0.82
     Half
    0.82
    HALF
    0.80
    half
    0.79
    Activations Density 0.129%

    No Known Activations