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. 14489
    Prev
    Next
    INDEX
    Explanations

    curly braces and HTML or XML-like tags in 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
     createContext
    -0.57
     potrivit
    -0.52
    asgi
    -0.52
     desideri
    -0.52
     linkovi
    -0.51
    Välislingid
    -0.49
     querr
    -0.49
     îna
    -0.48
    :✨
    -0.47
     فريبيس
    -0.47
    POSITIVE LOGITS
    Lähteet
    0.78
    +#+
    0.74
    DockStyle
    0.64
     OMITBAD
    0.59
     DbSet
    0.59
    Referencias
    0.57
    FontOfSize
    0.57
     թվական
    0.56
     للاسماء
    0.55
    endphp
    0.54
    Activations Density 0.235%

    No Known Activations