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. 3-GEMMASCOPE-RES-16K
    6. 11143
    Prev
    Next
    INDEX
    Explanations

    conjunctions related to and conditions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lovakia
    -0.54
    :][
    -0.52
    rogels
    -0.51
     archaeologist
    -0.49
    roglo
    -0.48
    OneToMany
    -0.48
    skyl
    -0.47
    
    -0.46
    ]=='
    -0.46
    htaccess
    -0.46
    POSITIVE LOGITS
     autorytatywna
    0.71
    حياتها
    0.71
    OGND
    0.70
    حياته
    0.69
    ViewChild
    0.62
    typeorm
    0.61
     okuyayım
    0.61
    :✨
    0.59
     NSCoder
    0.57
     تضيفلها
    0.56
    Activations Density 0.308%

    No Known Activations