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. 8-GEMMASCOPE-RES-16K
    6. 6059
    Prev
    Next
    INDEX
    Explanations

    instances of loop structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fij
    -0.59
    aarrggbb
    -0.59
     кра
    -0.58
     Sak
    -0.58
     للمعارف
    -0.54
     sak
    -0.54
    createObject
    -0.52
     remotely
    -0.52
     Empire
    -0.51
    noz
    -0.50
    POSITIVE LOGITS
    while
    0.97
    ImageContext
    0.91
    RenderAtEndOf
    0.88
    WaitGroup
    0.79
     المعيارى
    0.79
    Mientras
    0.77
    WHILE
    0.76
     délib
    0.75
    mientras
    0.74
    Cordialement
    0.73
    Activations Density 0.029%

    No Known Activations