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

    Neuronpedia

    APICircuit 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. 5-GEMMASCOPE-RES-16K
    6. 14184
    Prev
    Next
    INDEX
    Explanations

    terms related to changes in levels or status mentioned in a medical or scientific context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    至于
    -0.49
     Andromeda
    -0.46
     totul
    -0.46
     ellers
    -0.46
     Cæsar
    -0.45
     pilgrims
    -0.42
     Menü
    -0.42
     grosso
    -0.41
     Manzan
    -0.41
     المصدر
    -0.41
    POSITIVE LOGITS
    contentLoaded
    1.03
     оригіналу
    0.98
    InjectAttribute
    0.89
    RenderAtEndOf
    0.85
    تقاوى
    0.84
    elemField
    0.83
     InputDecoration
    0.81
    Lähteet
    0.80
    DockStyle
    0.79
    లాలు
    0.78
    Activations Density 0.593%

    No Known Activations