© 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. 13042
    Prev
    Next
    INDEX
    Explanations

    terms related to achievements and awards in competitive contexts

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

    winning or champions

    np_acts-logits-general · gemini-2.0-flash

    winning and claiming victory

    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
    zsche
    -0.58
    tanleria
    -0.56
    endpush
    -0.55
    ReactDOM
    -0.53
    Organisateur
    -0.52
    travis
    -0.51
    asantry
    -0.50
    SpringRunner
    -0.49
    ◀
    -0.49
    щность
    -0.48
    POSITIVE LOGITS
     winning
    1.22
     wins
    1.08
     win
    1.06
    Winning
    1.03
     décro
    0.96
     remporté
    0.91
    winning
    0.91
     giành
    0.88
     claim
    0.88
     Winning
    0.87
    Activations Density 0.161%

    No Known Activations