© 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 - 16k
    9. 17-GEMMASCOPE-RES-16K
    11. 2046
    Prev
    Next
    INDEX
    Explanations

    terms related to technical programming or mathematical functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sheets
    -0.53
    blad
    -0.47
    sheets
    -0.46
    Sheets
    -0.46
     Sheets
    -0.45
     competitive
    -0.45
     propriet
    -0.43
     Nationale
    -0.42
     monolithic
    -0.42
     period
    -0.41
    POSITIVE LOGITS
     point
    1.03
     points
    1.00
     coordinates
    0.99
     Point
    0.97
     Points
    0.96
     CGPoint
    0.95
    CGPoint
    0.94
     location
    0.91
    points
    0.90
     getLocation
    0.89
    Activations Density 0.929%

    No Known Activations