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. MLP Out - 16k
    5. 22-GEMMASCOPE-MLP-16K
    6. 15845
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables used in equations or expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.94
    findpost
    -0.88
    Хьажоргаш
    -0.79
    Архівовано
    -0.77
    BeginInit
    -0.75
     and
    -0.74
    الحياه
    -0.73
    تقاوى
    -0.69
    发表于
    -0.67
    styleType
    -0.66
    POSITIVE LOGITS
    ,
    1.28
    、
    0.70
    -,
    0.51
    ﹑
    0.47
    、
    0.45
    ・
    0.43
     calendriers
    0.41
    _,
    0.38
    、「
    0.38
    ,\,
    0.38
    Activations Density 1.903%

    No Known Activations