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. 7661
    Prev
    Next
    INDEX
    Explanations

    emphatic comparisons and the notion of exceeding or being greater than

    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
    jspx
    -0.69
     createState
    -0.65
    principalColumn
    -0.62
    __":
    -0.60
    !*\
    -0.57
     onAnimation
    -0.57
    utnik
    -0.57
     layui
    -0.57
    expandindo
    -0.57
    RegressionTest
    -0.57
    POSITIVE LOGITS
     blanches
    0.66
     estekak
    0.66
     själva
    0.63
     náv
    0.63
     NDEBUG
    0.61
     couverts
    0.58
     brancas
    0.56
     fiatal
    0.56
     pauvres
    0.56
     alimentaires
    0.56
    Activations Density 0.141%

    No Known Activations