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. 16-GEMMASCOPE-RES-16K
    6. 12790
    Prev
    Next
    INDEX
    Explanations

    technical terms and function calls related to shadow mapping and graphical object manipulation

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

    Code-related terms and symbols

    np_acts-logits-general · gemini-2.0-flash

    point, shadow, mark, control, position, status, standard, command, signal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wikispecies
    -0.77
     *__
    -0.74
    */].
    -0.73
     مشين
    -0.71
    ("")]
    
    -0.69
    >{"
    -0.66
    <>();
    
    -0.66
     QtGui
    -0.66
    ///</
    -0.65
    ]=="
    -0.64
    POSITIVE LOGITS
    (
    1.07
     (
    0.95
    (
    0.67
     InputDecoration
    0.57
     الحره
    0.52
     fermés
    0.52
     للاسماء
    0.52
     يتيمه
    0.50
     BoxDecoration
    0.48
     estekak
    0.47
    Activations Density 0.141%

    No Known Activations