© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110224
    Prev
    Next
    INDEX
    Explanations

    proper nouns and notable names within the text

    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
    XtraBars
    -0.52
     tatuagens
    -0.52
     borbo
    -0.50
     föruts
    -0.50
    IsMutable
    -0.50
    rungsseite
    -0.48
     rainha
    -0.47
     armonía
    -0.47
     chuva
    -0.47
     adaptación
    -0.46
    POSITIVE LOGITS
    ########.
    0.52
    MethodManager
    0.50
    참고
    0.41
     nahilalakip
    0.40
    AccessorTable
    0.38
    braio
    0.37
    甜甜
    0.35
     للاسماء
    0.35
     nakalista
    0.35
    dyr
    0.34
    Activations Density 0.116%

    No Known Activations