© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 13-GEMMASCOPE-RES-65K
    11. 16073
    Prev
    Next
    INDEX
    Explanations

    code-related elements, specifically headers and API request structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -1.16
    Controllo
    -0.93
    Autoritní
    -0.92
     autorytatywna
    -0.87
    fjspx
    -0.86
     cherchés
    -0.85
     numberOfRows
    -0.83
    تقاوى
    -0.75
     initComponents
    -0.72
    EndTag
    -0.70
    POSITIVE LOGITS
    GRANTED
    0.45
    addView
    0.43
    riwal
    0.42
     personal
    0.42
    кому
    0.42
    assertEquals
    0.42
     PackageManager
    0.41
    getMethod
    0.41
    章
    0.40
    fromCharCode
    0.40
    Activations Density 0.019%

    No Known Activations