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. 2298
    Prev
    Next
    INDEX
    Explanations

    references to specific characters or portions in texts

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

    "The" preceding capitalized words

    np_acts-logits-general · gemini-2.0-flash

    names of people, groups, and places

    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
     BoxDecoration
    -0.71
    __(/*!
    -0.64
    "]);
    -0.60
    iddhar
    -0.60
    itica
    -0.58
    GenerationType
    -0.57
    <>());
    -0.57
    )];
    
    -0.57
     "));
    -0.56
     disambiguazione
    -0.56
    POSITIVE LOGITS
     incomparable
    0.61
     inim
    0.60
     Dalai
    0.58
     likes
    0.57
    MemoryWarning
    0.52
    lma
    0.51
    ophilus
    0.50
    ੍ਹ
    0.49
    psies
    0.48
     Hadid
    0.48
    Activations Density 0.239%

    No Known Activations