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. 8646
    Prev
    Next
    INDEX
    Explanations

    attributes and properties of HTML or JSON elements

    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
     Max
    -0.59
     $
    -0.52
    able
    -0.52
     He
    -0.48
     to
    -0.48
     القدم
    -0.48
    Max
    -0.47
     max
    -0.46
     (
    -0.46
     with
    -0.45
    POSITIVE LOGITS
    extAlignment
    1.14
    endphp
    1.03
    ///</
    1.01
     Мексичка
    1.01
     StatelessWidget
    0.96
    -------------</
    0.95
    NUMX
    0.91
     beginnetje
    0.91
     للاسماء
    0.89
    Portail
    0.88
    Activations Density 0.276%

    No Known Activations