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. 4365
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate actions or events involving stopping or pausing, often in relation to the concept of time

    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
    audiovisuel
    -0.71
    UnitTesting
    -0.68
     disponibilités
    -0.67
    [])
    
    -0.67
    LookAnd
    -0.67
    Legături
    -0.65
    :✨
    -0.64
    recated
    -0.63
     thyself
    -0.61
    []);
    -0.61
    POSITIVE LOGITS
    vertret
    0.56
    Enqueue
    0.49
     await
    0.49
    ouds
    0.48
    enei
    0.47
     upang
    0.47
    ontin
    0.47
     sesi
    0.46
     să
    0.46
    chapters
    0.46
    Activations Density 0.160%

    No Known Activations