© 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. 10-GEMMASCOPE-RES-16K
    11. 11129
    Prev
    Next
    INDEX
    Explanations

    terms related to computational efficiency and performance metrics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    writeFieldEnd
    -0.73
    MessageTagHelper
    -0.65
    apimachinery
    -0.61
     trùng
    -0.59
    CharStream
    -0.57
    mybatisplus
    -0.55
    QPalette
    -0.55
    śle
    -0.55
    RetentionPolicy
    -0.55
    InstrumentedTest
    -0.54
    POSITIVE LOGITS
     memory
    0.59
     computation
    0.58
     Memory
    0.56
     slowdown
    0.54
     slowing
    0.54
     slow
    0.53
     CPU
    0.52
     optimization
    0.52
    slow
    0.52
     обращения
    0.51
    Activations Density 0.556%

    No Known Activations