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. 5-GEMMASCOPE-RES-16K
    6. 12110
    Prev
    Next
    INDEX
    Explanations

    instances of the word "draft" and related terms concerning manuscript preparation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Boeh
    -0.68
    styleUrls
    -0.67
     Moriarty
    -0.66
    zookeeper
    -0.65
     Kem
    -0.65
     Decker
    -0.65
    labelledby
    -0.63
    reness
    -0.63
    apimachinery
    -0.63
    rshire
    -0.62
    POSITIVE LOGITS
     draft
    2.53
     Draft
    2.43
     drafts
    2.41
    draft
    2.39
     DRAFT
    2.37
    Draft
    2.32
    DRAFT
    2.27
     drafted
    1.87
    rafts
    1.79
     drafting
    1.76
    Activations Density 0.068%

    No Known Activations