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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 12994
    Prev
    Next
    INDEX
    Explanations

    coding syntax and structure in programming documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BorderRadius
    -0.68
     оригіналу
    -0.66
     iconFacebook
    -0.65
     BorderSide
    -0.65
    =$?
    -0.64
    Amicalement
    -0.63
    </tfoot>
    -0.62
    mặt
    -0.62
    Baik
    -0.61
     $_"
    -0.60
    POSITIVE LOGITS
     للمعارف
    0.58
    ↵
    0.55
    IsContent
    0.54
    NewRow
    0.53
    ↵↵
    0.52
     frumo
    0.50
    cstring
    0.49
    SharedCtor
    0.48
    الإنجليزية
    0.47
    class
    0.47
    Activations Density 0.047%

    No Known Activations