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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-GEMMASCOPE-RES-16K
    6. 12385
    Prev
    Next
    INDEX
    Explanations

    references to operating systems and their components

    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
     ***!
    -0.71
     Perrin
    -0.67
    EndProject
    -0.64
    UnusedPrivate
    -0.63
     الرياضيه
    -0.63
     Irán
    -0.63
    Дереккөздер
    -0.62
    SerializeField
    -0.61
     Gelb
    -0.58
     Jule
    -0.57
    POSITIVE LOGITS
     OS
    2.04
    OS
    1.52
    操作系统
    0.94
     Os
    0.90
     ОС
    0.82
    Os
    0.77
     OSC
    0.74
     OSM
    0.72
     operating
    0.72
     Operating
    0.71
    Activations Density 0.159%

    No Known Activations