© 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. 5435
    Prev
    Next
    INDEX
    Explanations

    terms related to efficiency and effectiveness in various contexts

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

    "efficient" or "efficiency"

    np_acts-logits-general · gemini-2.0-flash

    efficiency and its contexts

    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
    дца
    -0.53
    WithMany
    -0.51
    setSubject
    -0.51
    hasNext
    -0.51
     Audiodateien
    -0.49
    abank
    -0.49
    ừng
    -0.48
    ltk
    -0.47
    گشت
    -0.47
    cestershire
    -0.47
    POSITIVE LOGITS
    tagHelperRunner
    0.95
     efficiencies
    0.85
     effic
    0.82
    mybatisplus
    0.82
    effic
    0.81
     itſelf
    0.81
    ICIENCY
    0.78
     énergétique
    0.78
    efficacité
    0.77
     uſed
    0.76
    Activations Density 0.161%

    No Known Activations