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. 4639
    Prev
    Next
    INDEX
    Explanations

    components and constructs related to object-relational mapping (ORM) and database interaction 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 @ 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
    ValueStyle
    -1.11
    Rhestr
    -1.01
    новниш
    -0.91
    WebVitals
    -0.90
    AndroidJUnit
    -0.89
    DockStyle
    -0.89
     StringTokenizer
    -0.87
    WebServlet
    -0.85
    AnchorStyles
    -0.85
    windowFixed
    -0.85
    POSITIVE LOGITS
    hibernate
    0.76
     Hibernate
    0.68
     EntityManager
    0.61
    SaveChanges
    0.61
     CoreData
    0.58
    ObjectContext
    0.58
    Hibernate
    0.57
    EntityFramework
    0.51
    entityManager
    0.42
     hibernate
    0.42
    Activations Density 0.141%

    No Known Activations