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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 11429
    Prev
    Next
    INDEX
    Explanations

    terms related to high technology and scientific research

    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
    Personensuche
    -0.66
    UserScript
    -0.62
    terly
    -0.57
    DataAnnotations
    -0.55
    Билгалдахарш
    -0.53
     BeautifulSoup
    -0.53
    󠁿
    -0.52
    ttal
    -0.51
    HasAnnotation
    -0.51
    astify
    -0.50
    POSITIVE LOGITS
     kysy
    0.54
     utford
    0.51
    <?>>
    0.51
    __(/*!
    0.50
     adipis
    0.50
     sélectionnés
    0.49
     vostri
    0.49
     devenus
    0.48
     perdana
    0.48
     éte
    0.47
    Activations Density 2.086%

    No Known Activations