© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 1966
    Prev
    Next
    INDEX
    Explanations

    references to threads and threading in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adaptation
    -0.33
    SerializeField
    -0.29
     adapting
    -0.29
     views
    -0.28
     asequ
    -0.28
     opposed
    -0.28
     best
    -0.28
     Fels
    -0.27
     aan
    -0.27
     als
    -0.27
    POSITIVE LOGITS
     thread
    1.61
     Thread
    1.55
    Thread
    1.41
     THREAD
    1.34
    thread
    1.32
     threads
    1.27
    THREAD
    1.13
     Threads
    1.13
     threaded
    1.11
    threads
    1.05
    Activations Density 0.251%

    No Known Activations