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. 25
    Prev
    Next
    INDEX
    Explanations

    terms related to blood group antigens and immunological factors

    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
     }}"></
    -0.54
     Herr
    -0.47
    كوم
    -0.47
     adem
    -0.46
    Sito
    -0.45
    single
    -0.45
    signol
    -0.45
     doğ
    -0.45
    logg
    -0.45
    Sheet
    -0.43
    POSITIVE LOGITS
     EconPapers
    0.86
    Obrázky
    0.71
     tags
    0.61
    tagext
    0.60
    TAGS
    0.58
    AnchorTagHelper
    0.58
    adpleegd
    0.58
     tagged
    0.57
    ILayout
    0.57
    ंदीखरीदारी
    0.57
    Activations Density 0.976%

    No Known Activations