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. 3802
    Prev
    Next
    INDEX
    Explanations

    sequences containing mathematical notation or symbols

    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
     sẻ
    -0.61
     kasarigan
    -0.57
    oida
    -0.54
    laration
    -0.53
    省市镇
    -0.52
    SCAPE
    -0.52
    signal
    -0.52
     Pingback
    -0.52
    cely
    -0.51
    جغرافيا
    -0.51
    POSITIVE LOGITS
    //
    0.70
     AssemblyProduct
    0.60
    marshaller
    0.60
    SizeMode
    0.60
     ویکی‌پدیای
    0.59
     imageNamed
    0.56
    Aiheesta
    0.56
    MethodManager
    0.54
    tagext
    0.53
    Composable
    0.52
    Activations Density 0.230%

    No Known Activations