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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 853
    Prev
    Next
    INDEX
    Explanations

    words with specific suffixes, particularly "-ly" and sometimes "-al"

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -0.64
    jspx
    -0.62
     CURLOPT
    -0.60
    ">//
    -0.60
     onAnimation
    -0.59
    CloseOperation
    -0.58
    protoimpl
    -0.58
    pement
    -0.56
    ///</
    -0.55
    scriptId
    -0.54
    POSITIVE LOGITS
     Efq
    0.52
    praš
    0.47
    cticut
    0.44
    جغرافيا
    0.44
    olesale
    0.44
    UpInside
    0.43
    原始内容存档于
    0.42
    SuccessListener
    0.42
    felves
    0.41
     محفوظة
    0.41
    Activations Density 12.985%

    No Known Activations