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. 12-GEMMASCOPE-RES-16K
    6. 2106
    Prev
    Next
    INDEX
    Explanations

    references to future prospects and developments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новниш
    -0.83
     Cardigan
    -0.77
     CommonModule
    -0.75
    nesty
    -0.71
     sherds
    -0.70
     bandera
    -0.70
     cardigan
    -0.70
     tää
    -0.70
     sén
    -0.70
    dormit
    -0.69
    POSITIVE LOGITS
     future
    1.37
    FUTURE
    1.35
     FUTURE
    1.34
    tableFuture
    1.33
     Future
    1.32
    Future
    1.22
    future
    1.22
     futura
    1.17
     futures
    1.07
     Past
    1.06
    Activations Density 0.065%

    No Known Activations