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. 4007
    Prev
    Next
    INDEX
    Explanations

    references to data points or highlighting points of interest

    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
     Theſe
    -0.92
    Autoritní
    -0.89
     DELLE
    -0.88
    ChildScrollView
    -0.85
    ſelf
    -0.78
     MainAxisSize
    -0.78
     onCancelled
    -0.77
     yoksa
    -0.72
     Majefty
    -0.72
     Barbier
    -0.72
    POSITIVE LOGITS
     POINT
    2.29
     point
    2.29
    point
    2.22
     points
    2.18
     Point
    2.15
    Point
    2.08
    POINT
    2.07
    points
    1.99
     Points
    1.94
     POINTS
    1.89
    Activations Density 0.065%

    No Known Activations