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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 109504
    Prev
    Next
    INDEX
    Explanations

    references to Amazon Resource Names (ARNs)

    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
    arn
    -2.53
    ARN
    -1.88
    arns
    -1.40
    Arn
    -1.33
     Arn
    -1.32
     arn
    -1.27
    arna
    -1.22
    arned
    -1.06
    arnas
    -1.04
     ARN
    -1.02
    POSITIVE LOGITS
     myſelf
    0.61
    tanleria
    0.50
     estekak
    0.49
    MessageTagHelper
    0.47
     Jefus
    0.45
    ſelves
    0.43
     Cæsar
    0.42
    AxisAlignment
    0.41
     الرياضيه
    0.41
     Houſe
    0.41
    Activations Density 0.002%

    No Known Activations