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. 20-GEMMASCOPE-RES-16K
    6. 6341
    Prev
    Next
    INDEX
    Explanations

    color specifications and formatting in coding or graphical settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dignité
    -0.75
    devamını
    -0.71
     verità
    -0.66
    enumi
    -0.65
     مشين
    -0.65
     विश्वसनीयता
    -0.65
     vérit
    -0.63
     ouvriers
    -0.62
     dimentic
    -0.62
     termica
    -0.61
    POSITIVE LOGITS
    arschu
    0.54
    ApiModelProperty
    0.48
     internetowa
    0.47
     Penh
    0.46
     berk
    0.45
    Computed
    0.45
     interp
    0.44
    advertisement
    0.44
     hus
    0.44
    curité
    0.43
    Activations Density 0.066%

    No Known Activations