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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 15420
    Prev
    Next
    INDEX
    Explanations

    words related to processes, systems, or measures in technical or scientific contexts

    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
     ་་
    -1.01
     iſt
    -0.92
    ſelf
    -0.91
     itſelf
    -0.91
     Theſe
    -0.91
    ſelves
    -0.89
     ſind
    -0.89
     whoſe
    -0.87
     raiſ
    -0.85
    >\<^
    -0.84
    POSITIVE LOGITS
    
    0.80
    -
    0.60
     فريبيس
    0.54
    e
    0.54
    i
    0.54
    g
    0.54
    出版年
    0.52
    UVWXYZ
    0.52
     vzduchu
    0.52
    hpur
    0.51
    Activations Density 0.134%

    No Known Activations