© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14657
    Prev
    Next
    INDEX
    Explanations

    references to app components or files in programming 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
    SourceChecksum
    -1.14
    :✨
    -1.09
    GEBURTSDATUM
    -1.04
    TagMode
    -1.02
    djangoproject
    -1.02
    webElementXpaths
    -1.01
    AndEndTag
    -0.98
     CreateTagHelper
    -0.97
     defaultstate
    -0.96
     resourceCulture
    -0.96
    POSITIVE LOGITS
    rouge
    0.47
     Toolbox
    0.45
     most
    0.44
    сього
    0.41
     vis
    0.41
    งาม
    0.40
     slide
    0.40
     freg
    0.40
     arşivlendi
    0.40
     tá
    0.39
    Activations Density 0.001%

    No Known Activations