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. 2577
    Prev
    Next
    INDEX
    Explanations

    definitions of classes in programming code

    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
    Portail
    -0.77
    Билгалдахарш
    -0.68
    DockStyle
    -0.67
     Pristupljeno
    -0.65
     مشارکت‌کنندگان
    -0.63
    Ạ
    -0.61
    Hozzáférés
    -0.58
    colgroup
    -0.58
    Portale
    -0.58
    MultipartFile
    -0.57
    POSITIVE LOGITS
    Personensuche
    0.74
     صوتيه
    0.59
     noDo
    0.55
     فريبيس
    0.54
    protoc
    0.52
     Normdatei
    0.50
    ChromeDriver
    0.50
    Hauptartikel
    0.49
    horabuena
    0.48
     comuniques
    0.48
    Activations Density 0.035%

    No Known Activations