© 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. 21-GEMMASCOPE-RES-16K
    11. 2107
    Prev
    Next
    INDEX
    Explanations

    technical terms related to time measurement and timing functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cinoma
    -0.59
    pubmed
    -0.51
    SPOT
    -0.51
    ParallelGroup
    -0.51
    arent
    -0.49
    DAB
    -0.49
    cinogenicity
    -0.48
    MemoryWarning
    -0.48
     typelib
    -0.48
    webElementXpaths
    -0.47
    POSITIVE LOGITS
     micro
    0.81
     milliseconds
    0.78
     nano
    0.78
     ns
    0.76
     ms
    0.76
    nano
    0.74
    micro
    0.72
     clock
    0.71
    Micro
    0.71
     duration
    0.71
    Activations Density 0.511%

    No Known Activations