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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108415
    Prev
    Next
    INDEX
    Explanations

    references to characters in 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
     characters
    -1.93
     Characters
    -1.79
    characters
    -1.70
    Characters
    -1.67
     CHARACTERS
    -1.55
     personajes
    -1.17
     personagens
    -1.13
     personnages
    -1.05
     caractères
    -1.04
     caracteres
    -1.02
    POSITIVE LOGITS
    parsedMessage
    0.58
     kaarangay
    0.56
    createNewFile
    0.54
    
    0.54
     الحره
    0.52
     وتسجيلات
    0.52
     hiker
    0.51
    Билгалдахарш
    0.50
     gynhyrchwyd
    0.50
    期刊论文
    0.49
    Activations Density 0.005%

    No Known Activations