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. 21-GEMMASCOPE-RES-16K
    6. 571
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming-related symbols and constructs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    twimg
    -0.43
     geleverd
    -0.41
    couz
    -0.41
    WebElementEntity
    -0.41
     poulet
    -0.40
    ganet
    -0.39
    uws
    -0.39
    MultipartFile
    -0.38
    ContentAsync
    -0.37
    ṳ
    -0.37
    POSITIVE LOGITS
     B
    1.01
    B
    0.94
     b
    0.92
     BB
    0.85
    b
    0.82
    beta
    0.81
     BI
    0.77
    BM
    0.76
     bb
    0.76
     BC
    0.76
    Activations Density 1.538%

    No Known Activations