Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 13742
    Prev
    Next
    INDEX
    Explanations

    keywords and function calls related to threading and synchronization mechanisms in programming

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

    Code-related locks (mutex, rlock, LOCK_NB, etc.)

    np_acts-logits-general · gemini-2.0-flash

    locks and mutexes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    loem
    -0.45
    bogen
    -0.43
    olingo
    -0.43
     Powered
    -0.43
     zwy
    -0.43
    bray
    -0.43
     overboard
    -0.42
    SUGGEST
    -0.41
    ekt
    -0.41
     Instinct
    -0.40
    POSITIVE LOGITS
     lock
    1.55
    lock
    1.49
     Lock
    1.39
    Lock
    1.35
     locks
    1.33
     locking
    1.27
     LOCK
    1.27
    LOCK
    1.26
     mutex
    1.22
    locks
    1.22
    Activations Density 0.348%

    No Known Activations