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. 3137
    Prev
    Next
    INDEX
    Explanations

    specific class types and programming constructs within code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code that uses "implements", "extends", or ":"

    np_acts-logits-general · gemini-2.0-flash

    class implements interface

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     تانيه
    -0.65
    ("}");
    -0.62
    ➟
    -0.62
    发表于
    -0.59
    SequentialGroup
    -0.58
     =>
    
    -0.57
    "](
    -0.57
    ()['
    -0.55
     autorytatywna
    -0.54
    numerusform
    -0.54
    POSITIVE LOGITS
     implements
    0.97
    implements
    0.74
     esternos
    0.54
     Pública
    0.54
    <?
    0.52
     implement
    0.50
    Население
    0.48
     кӀош
    0.48
     undertakes
    0.47
    Implementing
    0.46
    Activations Density 0.062%

    No Known Activations