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. 13-GEMMASCOPE-RES-16K
    6. 13384
    Prev
    Next
    INDEX
    Explanations

    code-related structures and elements, likely related to programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InputTagHelper
    -0.71
    OGND
    -0.67
    printLine
    -0.64
    writeFieldEnd
    -0.60
    LabelTagHelper
    -0.58
     tartalomajánló
    -0.54
     '\\;'
    -0.53
    NoSuchAlgorithm
    -0.52
     composés
    -0.51
     lehetős
    -0.51
    POSITIVE LOGITS
    ="../
    0.82
     обращения
    0.72
    cpp
    0.69
    ClientSize
    0.68
    loadModel
    0.65
     filename
    0.63
    AccessorTable
    0.58
    toggler
    0.58
     مشين
    0.58
     ویکی‌پدیای
    0.58
    Activations Density 0.053%

    No Known Activations