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. 6-GEMMASCOPE-MLP-16K
    6. 62
    Prev
    Next
    INDEX
    Explanations

    phrases and words in the Russian language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ведении
    -0.57
     anyway
    -0.54
    getAs
    -0.52
     theme
    -0.46
    عام
    -0.46
    茄
    -0.46
     موا
    -0.45
    ведения
    -0.45
     May
    -0.44
    čni
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.95
    rungsseite
    0.88
     ProtoMessage
    0.85
    ंदीखरीदारी
    0.83
    下载附件
    0.77
     nahilalakip
    0.76
    ollectionView
    0.75
    دانشنامهٔ
    0.74
    #+#
    0.73
    mybatisplus
    0.73
    Activations Density 0.179%

    No Known Activations