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. 14215
    Prev
    Next
    INDEX
    Explanations

    code-related elements and constructs in programming

    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
     Nauk
    -0.54
    ']));
    -0.54
    }`).
    -0.54
    }`);
    -0.54
     myſelf
    -0.53
    "){
    
    -0.53
     Causeway
    -0.51
     Nant
    -0.51
     */,
    -0.51
    ')";
    -0.50
    POSITIVE LOGITS
     resourceCulture
    0.72
    BeginContext
    0.67
    ?
    0.66
     OMITBAD
    0.63
     محفوظة
    0.63
     الحره
    0.63
     cherchés
    0.62
    клопе
    0.60
    tvguidetime
    0.59
    帖最后由
    0.59
    Activations Density 0.058%

    No Known Activations