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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109745
    Prev
    Next
    INDEX
    Explanations

    instances of the word "remember"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     kasarigan
    -0.79
    دانشنامهٔ
    -0.78
     للمعارف
    -0.64
    utives
    -0.63
     nakalista
    -0.62
     الرياضيه
    -0.61
    RTLR
    -0.59
    RectangleBorder
    -0.58
    Хьажоргаш
    -0.56
     AssemblyCompany
    -0.56
    POSITIVE LOGITS
    AddTagHelper
    0.32
    хай
    0.32
     defence
    0.31
     sta
    0.31
     BLOG
    0.29
     Cancer
    0.28
    HasBeenSet
    0.28
     BIEN
    0.28
     Daily
    0.28
     defenders
    0.28
    Activations Density 0.001%

    No Known Activations