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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 10-GEMMASCOPE-RES-16K
    6. 13229
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to advancements and innovations in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     themſelves
    -0.66
     myſelf
    -0.64
     becauſe
    -0.62
     ſeveral
    -0.58
     Monfieur
    -0.58
     whoſe
    -0.57
     ſuch
    -0.57
     faptul
    -0.56
    agd
    -0.55
     ainfi
    -0.54
    POSITIVE LOGITS
     propOrder
    0.84
    Sklici
    0.77
    Autoritní
    0.74
     ffilmiau
    0.64
    azan
    0.64
    DECREF
    0.64
    anskje
    0.63
    kegaard
    0.62
     bağlantılar
    0.61
    ///</
    0.61
    Activations Density 0.639%

    No Known Activations