© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 2425
    Prev
    Next
    INDEX
    Explanations

    terms related to delays and latency in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    %}
    -0.70
    Liet
    -0.63
    Petsc
    -0.61
     Brooke
    -0.58
    +')
    -0.57
     MacKenzie
    -0.57
     rapports
    -0.56
     Benn
    -0.56
     BoxFit
    -0.56
    uth
    -0.55
    POSITIVE LOGITS
     delay
    2.92
     Delay
    2.77
     delays
    2.72
     DELAY
    2.68
    delay
    2.65
     Delays
    2.56
    Delay
    2.44
     delayed
    2.29
    DELAY
    2.24
     delaying
    2.20
    Activations Density 0.056%

    No Known Activations