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. 12-GEMMASCOPE-RES-16K
    6. 1689
    Prev
    Next
    INDEX
    Explanations

    technical terms and references related to software development and coding

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ropical
    -0.49
    liothèque
    -0.49
    zama
    -0.48
    substack
    -0.48
    gerufen
    -0.47
     заба
    -0.47
     Svenska
    -0.45
     Мексичка
    -0.45
     lays
    -0.45
    gibt
    -0.44
    POSITIVE LOGITS
     ویکی‌پدیا
    0.96
    IVEREF
    0.80
    Personendaten
    0.76
     saites
    0.70
    +#+
    0.69
     CreateTagHelper
    0.66
     BrowserModule
    0.65
    webElementXpaths
    0.64
    WebElementEntity
    0.63
    Diwedd
    0.63
    Activations Density 1.810%

    No Known Activations