© 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. 24-GEMMASCOPE-RES-16K
    6. 8908
    Prev
    Next
    INDEX
    Explanations

    references to threading concepts and their potential issues, particularly focusing on process management and deadlocks

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

    threads or threading

    np_acts-logits-general · gemini-2.0-flash

    starting or managing threads

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.54
     nakalista
    -0.52
    étrie
    -0.52
    olingo
    -0.52
    éez
    -0.48
    didSet
    -0.48
    nodoc
    -0.47
     Hump
    -0.47
     Cristal
    -0.47
     quý
    -0.47
    POSITIVE LOGITS
     thread
    2.13
     Thread
    2.02
     threads
    1.91
    Thread
    1.88
    thread
    1.86
     THREAD
    1.77
     Threads
    1.67
    Threads
    1.55
    threads
    1.53
    THREAD
    1.52
    Activations Density 0.361%

    No Known Activations