© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 57821
    Prev
    Next
    INDEX
    Explanations

    references to mutexes and synchronization in the code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    r
    -0.74
    n
    -0.69
     Haan
    -0.67
     Yn
    -0.62
    Y
    -0.61
     plá
    -0.61
     Fanny
    -0.61
    GR
    -0.60
    l
    -0.59
    v
    -0.57
    POSITIVE LOGITS
     mutex
    1.59
    mutex
    1.38
    Mutex
    1.14
     Mute
    1.10
    Muz
    0.97
     Murdock
    0.88
     neceff
    0.85
     Mugabe
    0.84
    XmlAccessorType
    0.81
    uxedo
    0.80
    Activations Density 0.011%

    No Known Activations