© 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. 2067
    Prev
    Next
    INDEX
    Explanations

    annotations and decorators commonly used in programming languages

    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
     iprot
    -0.87
    mybatisplus
    -0.72
    ContentAlignment
    -0.68
     resourceCulture
    -0.68
    InputTagHelper
    -0.65
     ***!
    -0.62
    IndentedString
    -0.61
    ⓧ
    -0.61
     Bessel
    -0.59
    Халык
    -0.58
    POSITIVE LOGITS
    ValueStyle
    0.62
    XmlRootElement
    0.61
    ("")]
    0.61
    veien
    0.58
    oxin
    0.57
    raine
    0.57
    extAlignment
    0.56
    otheses
    0.56
     Veel
    0.56
    MIB
    0.54
    Activations Density 0.001%

    No Known Activations