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. 13800
    Prev
    Next
    INDEX
    Explanations

    references to data types related to byte arrays and files

    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
    onOptions
    -0.98
     okuyayım
    -0.95
    NameInMap
    -0.86
    ="#"><
    -0.86
    RUnlock
    -0.86
     وتسجيلات
    -0.79
     &___
    -0.79
    #
    -0.78
    Erreferentziak
    -0.78
    coln
    -0.76
    POSITIVE LOGITS
     byte
    1.58
     Byte
    1.54
     bytes
    1.51
    bytes
    1.45
    Byte
    1.44
    Bytes
    1.42
    byte
    1.39
     BYTE
    1.28
     Bytes
    1.27
    BYTES
    1.25
    Activations Density 0.166%

    No Known Activations