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. 7452
    Prev
    Next
    INDEX
    Explanations

    dates and specific quantitative values in the text

    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
    '],$
    -0.85
    ']=$
    -0.72
    '],
    
    -0.71
    anskje
    -0.71
    <bos>
    -0.69
    ///</
    -0.64
    )|^{
    -0.64
    })*/
    -0.64
    "],
    
    -0.64
    )}_
    -0.63
    POSITIVE LOGITS
     kaynağından
    0.67
     للمعارف
    0.65
    :
    0.63
    ագրություններ
    0.62
    FormTagHelper
    0.48
     idem
    0.48
    таратура
    0.46
    none
    0.44
     –
    0.44
    Obrázky
    0.43
    Activations Density 0.268%

    No Known Activations