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. 2398
    Prev
    Next
    INDEX
    Explanations

    references to the concept of 'self' in programming contexts

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

    Python's "self" keyword in method definitions

    np_acts-logits-general · gemini-2.0-flash

    class methods and attributes

    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
    '],'
    -0.67
    <>
    
    -0.57
    /</
    -0.56
    ']),
    -0.56
    RegistryLite
    -0.54
    انيف
    -0.53
    numerusform
    -0.53
    '));
    
    -0.53
    ')),
    -0.51
    ']));
    -0.50
    POSITIVE LOGITS
    EndInit
    0.69
     للاسماء
    0.64
    knapp
    0.58
    WEBPACK
    0.57
    NUMX
    0.53
    postIndex
    0.53
     NgModule
    0.52
    complexType
    0.52
     виправивши
    0.51
     HttpNotFound
    0.51
    Activations Density 0.019%

    No Known Activations