© 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. 16-GEMMASCOPE-RES-16K
    11. 1332
    Prev
    Next
    INDEX
    Explanations

    names of sports figures and managers, especially in the context of team performance

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

    Mention of players retiring or returning

    np_acts-logits-general · gemini-2.0-flash

    retired or retirement

    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
    +#+#
    -0.58
     veille
    -0.55
     cresce
    -0.54
     preuve
    -0.51
     nacer
    -0.51
     médié
    -0.50
     soulign
    -0.49
    íslu
    -0.49
     gadis
    -0.49
     crecer
    -0.49
    POSITIVE LOGITS
     retired
    0.88
     retirement
    0.76
    retired
    0.73
    Retired
    0.72
     comeback
    0.71
     Retired
    0.71
     retirees
    0.66
     reti
    0.64
    retirement
    0.64
     retir
    0.63
    Activations Density 0.261%

    No Known Activations