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. 5-GEMMASCOPE-RES-16K
    6. 11909
    Prev
    Next
    INDEX
    Explanations

    references to new technologies or platforms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IGraphics
    -0.60
    fluence
    -0.60
     back
    -0.55
     front
    -0.55
    //
    -0.54
    umal
    -0.52
     &=&
    -0.52
    acor
    -0.51
     prospec
    -0.51
    "",
    
    -0.50
    POSITIVE LOGITS
     betweenstory
    0.86
    IsMutable
    0.83
     مشين
    0.77
    DoubleQuotes
    0.74
    出版年
    0.71
     Normdatei
    0.71
    tvguidetime
    0.68
     @"/
    0.65
     purpoſe
    0.63
    ſelves
    0.62
    Activations Density 0.011%

    No Known Activations