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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109884
    Prev
    Next
    INDEX
    Explanations

    terms associated with scientific or technical specifications and references

    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
     खरीदा
    -0.36
     ejus
    -0.30
     genommen
    -0.28
    [::-
    -0.28
     Cer
    -0.28
    DataBind
    -0.27
     dumne
    -0.27
    няка
    -0.26
    jahres
    -0.26
     SCHE
    -0.26
    POSITIVE LOGITS
    ScopeManager
    0.71
     MainAxisSize
    0.58
     kasarigan
    0.58
    AsUp
    0.57
    webElementXpaths
    0.57
    :✨
    0.56
     архивлан
    0.54
    Хьажоргаш
    0.54
    tanleria
    0.53
    出版年
    0.52
    Activations Density 0.069%

    No Known Activations