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. 5-GEMMASCOPE-RES-16K
    6. 7444
    Prev
    Next
    INDEX
    Explanations

    concepts and parameters related to lighting in a 3D graphics context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Jeografia
    -0.66
     Мексичка
    -0.62
    afficheront
    -0.61
    StoreMessageInfo
    -0.61
     inflater
    -0.60
    +:+
    -0.60
    PageContext
    -0.60
    ReusableCell
    -0.58
    ammlung
    -0.58
    Наде
    -0.58
    POSITIVE LOGITS
    prefixer
    0.68
     الرياضيه
    0.64
    MessageTagHelper
    0.56
    InfoWindow
    0.49
    iibo
    0.49
    DataAnnotations
    0.48
    MENAFN
    0.48
    Bioaccumulative
    0.47
     henvisninger
    0.47
    Portály
    0.46
    Activations Density 1.375%

    No Known Activations