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. 9726
    Prev
    Next
    INDEX
    Explanations

    numbers associated with risk or medical data

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

    numbers in the 70s range, especially when they appear as standalone tokens or inside mathematical expressions and references.

    oai_token-act-pair · gpt-5Triggered by @arielgoldsteinlab
    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
    hwar
    -0.67
     Edwards
    -0.65
    梓
    -0.64
     Puff
    -0.64
     cách
    -0.62
     Mih
    -0.61
     Ayres
    -0.61
    γχ
    -0.58
     предложение
    -0.58
    ElementException
    -0.57
    POSITIVE LOGITS
    transQ
    0.85
     Sarm
    0.82
    atorze
    0.77
    Kaynakça
    0.75
     Yarm
    0.73
     nonUne
    0.73
    NOPQRST
    0.72
    typeorm
    0.71
     Martine
    0.70
     Sénat
    0.69
    Activations Density 0.330%

    No Known Activations