Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 20-GEMMASCOPE-RES-16K
    6. 1492
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    LaTeX math expressions

    np_acts-logits-general · gemini-2.0-flash

    mathematical punctuation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     Rodrigues
    -0.61
     Ser
    -0.56
    savevideo
    -0.55
    یتی
    -0.55
    pendium
    -0.55
    :],
    -0.53
    ribune
    -0.53
     tartalomajánló
    -0.53
    IPMENT
    -0.52
    kalender
    -0.52
    POSITIVE LOGITS
     itſelf
    0.83
     CreateTagHelper
    0.78
     kanya
    0.75
     houſe
    0.74
     AssemblyCulture
    0.72
     purpoſe
    0.72
    riwal
    0.70
     Efq
    0.69
    IGraphics
    0.69
    tableFuture
    0.68
    Activations Density 0.519%

    No Known Activations