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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43194
    Prev
    Next
    INDEX
    Explanations

    punctuation and delimiters used in programming and data structures

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ArrowToggle
    -0.65
     defaultstate
    -0.64
    SPO
    -0.54
    Manbalar
    -0.51
    струкция
    -0.50
    uolo
    -0.49
    ValuePair
    -0.48
    alige
    -0.47
    pll
    -0.47
     Plots
    -0.47
    POSITIVE LOGITS
     незавершена
    0.66
     оригіналу
    0.66
    AnchorStyles
    0.64
    tagHelper
    0.62
    consulté
    0.61
     StatefulWidget
    0.60
    CodeAttribute
    0.60
    dry
    0.59
    Datuak
    0.59
     consultato
    0.57
    Activations Density 0.011%

    No Known Activations