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. 8-GEMMASCOPE-RES-16K
    6. 8645
    Prev
    Next
    INDEX
    Explanations

    technical terms related to boundary conditions in differential equations

    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
     themselves
    -0.47
     conflits
    -0.46
     risks
    -0.44
     riscos
    -0.43
     conflicts
    -0.41
     risco
    -0.41
    KURZBESCHREIBUNG
    -0.41
     risk
    -0.40
     crystall
    -0.40
    amer
    -0.40
    POSITIVE LOGITS
     للمعارف
    0.93
     AssemblyTitle
    0.88
     समीक्षक
    0.78
     consultato
    0.77
    最快更新
    0.73
     initComponents
    0.69
    sizeCache
    0.68
    UnusedPrivate
    0.66
    MIDDLEWARE
    0.65
     useAppContext
    0.63
    Activations Density 0.626%

    No Known Activations