© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8552
    Prev
    Next
    INDEX
    Explanations

    significant historical events

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

    "celebrating" or "effects"

    np_acts-logits-general · gemini-2.0-flash

    celebrating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BASEPATH
    -0.52
    KommentareTeilen
    -0.51
    ThroughAttribute
    -0.49
    MENAFN
    -0.48
    mij
    -0.46
     attic
    -0.46
    WebVitals
    -0.46
     bidder
    -0.46
     ladder
    -0.46
    (&$
    -0.43
    POSITIVE LOGITS
     celebration
    1.00
     celebrates
    0.96
     celebrating
    0.96
     celebrate
    0.94
    celebr
    0.88
     commemorating
    0.87
     celebrations
    0.87
    Celebrate
    0.86
    Celebrating
    0.86
    celebrate
    0.86
    Activations Density 0.193%

    No Known Activations