© 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. 11934
    Prev
    Next
    INDEX
    Explanations

    references to different versions or adaptations of a product or content

    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
     חיצוניים
    -0.77
    ViewImports
    -0.69
     betweenstory
    -0.69
    はじめに
    -0.67
     autorytatywna
    -0.67
    ContentAsync
    -0.65
    ServletException
    -0.65
    AddTagHelper
    -0.63
    HasForeignKey
    -0.60
    ImageContext
    -0.60
    POSITIVE LOGITS
     version
    3.42
     versions
    2.97
    version
    2.69
     versión
    2.57
     Version
    2.49
     VERSION
    2.42
     versão
    2.34
     versione
    2.33
    版本
    2.32
    Version
    2.30
    Activations Density 1.016%

    No Known Activations