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. 13-GEMMASCOPE-RES-16K
    6. 14450
    Prev
    Next
    INDEX
    Explanations

    references to time-based services and availability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedCtor
    -0.76
    /**
    -0.68
     للاسماء
    -0.66
     noqa
    -0.65
     BSEB
    -0.63
    goa
    -0.63
    //
    -0.62
     SPDX
    -0.62
    sizeCache
    -0.62
     Kader
    -0.61
    POSITIVE LOGITS
     night
    0.84
     midnight
    0.81
     суток
    0.77
    midnight
    0.73
     overnight
    0.72
     nighttime
    0.72
     сутки
    0.69
     nacht
    0.68
    night
    0.68
     nocturnal
    0.68
    Activations Density 0.126%

    No Known Activations