© 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. 4789
    Prev
    Next
    INDEX
    Explanations

    patterns related to code syntax, specifically for query selectors and function calls in JavaScript

    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
    IsMutable
    -0.58
    HasAnnotation
    -0.58
    twimg
    -0.52
    icago
    -0.50
    setObjectName
    -0.49
    StreamReader
    -0.48
    фак
    -0.48
    맞
    -0.47
    campe
    -0.45
    1
    -0.44
    POSITIVE LOGITS
    WebElementEntity
    0.91
     $('
    0.78
     $_"
    0.77
    >{@
    0.75
     مواليد
    0.74
    "]/
    0.73
     $("
    0.73
    UrlResolution
    0.72
    ">:
    0.71
    antMatchers
    0.71
    Activations Density 0.007%

    No Known Activations