Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 7047
    Prev
    Next
    INDEX
    Explanations

    elements of a programming code or XML-like structure

    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
     bibir
    -0.47
    "){
    -0.45
     समीक्षाएं
    -0.44
    ğlık
    -0.43
    "){
    
    -0.42
    Provided
    -0.42
     case
    -0.41
    ¶
    -0.41
    фициальный
    -0.41
     décider
    -0.40
    POSITIVE LOGITS
     getItemCount
    0.83
    MemoryWarning
    0.73
     "..\..\
    0.71
     BrowserModule
    0.70
    Autoritní
    0.70
    Personensuche
    0.69
     AssemblyVersion
    0.67
     propOrder
    0.65
     "..\..\..\
    0.65
    invokeLater
    0.65
    Activations Density 0.063%

    No Known Activations