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. 4324
    Prev
    Next
    INDEX
    Explanations

    terms related to 3D geometry and positioning in a programming 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
     perdana
    -0.50
    expandindo
    -0.49
     packageName
    -0.49
     Baal
    -0.49
    ähig
    -0.48
    Хьажоргаш
    -0.47
    ாள
    -0.47
     launched
    -0.47
    inghouse
    -0.47
    OfYear
    -0.47
    POSITIVE LOGITS
    IntoConstraints
    1.20
    LLocation
    0.95
    localPosition
    0.90
     location
    0.89
    makeConstraints
    0.85
    Position
    0.81
     LOCATION
    0.79
     CGPoint
    0.78
     coordinates
    0.78
     MotionEvent
    0.77
    Activations Density 0.332%

    No Known Activations