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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 3-GEMMASCOPE-RES-16K
    6. 6186
    Prev
    Next
    INDEX
    Explanations

    Java package and import statements that reference utility classes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    */),
    -0.51
    eabouts
    -0.51
     antworte
    -0.51
    bilisi
    -0.50
    {}/
    -0.49
     Oedipus
    -0.48
     betweenstory
    -0.48
    ỗi
    -0.47
     leaſt
    -0.47
    ERTS
    -0.46
    POSITIVE LOGITS
    
    0.89
     PhpStorm
    0.80
    ChildScrollView
    0.80
    WaitGroup
    0.75
     дописавши
    0.72
     disambiguazione
    0.70
    gulier
    0.69
     nahilalakip
    0.68
     محفوظة
    0.68
    styleType
    0.67
    Activations Density 0.018%

    No Known Activations