© 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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15580
    Prev
    Next
    INDEX
    Explanations

    export and function declarations in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteTagHelper
    -0.62
    WriteAttribute
    -0.59
    COLN
    -0.59
    awtextra
    -0.58
    enfone
    -0.58
    XmlEnum
    -0.58
    lucene
    -0.57
     SafeMath
    -0.56
    riki
    -0.56
     addSubview
    -0.56
    POSITIVE LOGITS
    export
    1.50
     export
    1.23
     exports
    0.90
    const
    0.82
     exported
    0.81
     interface
    0.79
     exporting
    0.78
     Export
    0.76
     EXPORT
    0.75
    interface
    0.72
    Activations Density 0.063%

    No Known Activations