Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 14905
    Prev
    Next
    INDEX
    Explanations

    references to zip file handling and related libraries in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Савезне
    -1.00
    Erreferentziak
    -0.92
    Ծանոթ
    -0.89
    HasAnnotation
    -0.88
     kasarigan
    -0.85
    تقاوى
    -0.84
    رشف
    -0.82
    XmlAccessorType
    -0.79
    Gambas
    -0.78
     Normdatei
    -0.78
    POSITIVE LOGITS
    yı
    0.58
    zip
    0.56
     plat
    0.52
    نه
    0.52
     pelo
    0.52
     Dra
    0.52
     hos
    0.51
    IMPORTED
    0.51
    zi
    0.51
    生
    0.50
    Activations Density 2.106%

    No Known Activations