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. 2847
    Prev
    Next
    INDEX
    Explanations

    references to traditional Chinese medicine and its formulas

    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
    StoryboardSegue
    -1.09
     NSCoder
    -0.91
     дописавши
    -0.89
     препратки
    -0.86
     ProtoMessage
    -0.85
    twimg
    -0.85
     CreateTagHelper
    -0.81
     onCreateView
    -0.79
     jScrollPane
    -0.79
    ագրություններ
    -0.77
    POSITIVE LOGITS
     method
    0.53
     gran
    0.47
    <bos>
    0.46
     system
    0.46
     performance
    0.46
     mode
    0.45
     list
    0.45
    fö
    0.43
    ={({
    0.43
     background
    0.43
    Activations Density 0.468%

    No Known Activations