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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 90025
    Prev
    Next
    INDEX
    Explanations

    terms related to recursion and cyclic structures in programming or computational contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     air
    -0.35
    sptr
    -0.35
     cold
    -0.34
     baguette
    -0.33
     defray
    -0.33
     cost
    -0.33
    Demografía
    -0.32
    ính
    -0.29
     پر
    -0.29
    clazz
    -0.28
    POSITIVE LOGITS
     PeEnEo
    0.75
    verifyException
    0.74
     '\\;'
    0.68
     ویکی‌پدی
    0.66
    ſelf
    0.66
    verwijspagina
    0.65
    tanleria
    0.63
     snippetHide
    0.62
     kasarigan
    0.61
    最快更新
    0.60
    Activations Density 0.084%

    No Known Activations