© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1342
    Prev
    Next
    INDEX
    Explanations

    keywords related to data manipulation and structure operations

    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
    AutoModerator
    -0.54
    yonel
    -0.53
    chita
    -0.52
    itola
    -0.50
    hyrchwyd
    -0.50
     Sass
    -0.47
     Wayback
    -0.47
    jsonwebtoken
    -0.47
    Ál
    -0.46
    fusc
    -0.45
    POSITIVE LOGITS
                            
    0.94
    0.78
                             
    0.69
                              
    0.64
                           
    0.63
    AddTagHelper
    0.61
    OGND
    0.59
    لينكات
    0.57
                          
    0.57
     Thirdly
    0.56
    Activations Density 0.103%

    No Known Activations