© 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. 108910
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their significance 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
     stel
    -0.43
    antidad
    -0.43
     kimi
    -0.43
     HOLD
    -0.42
    ilige
    -0.42
    iempos
    -0.42
    uchte
    -0.41
    rouvez
    -0.41
    isela
    -0.41
     FORGET
    -0.41
    POSITIVE LOGITS
    parsedMessage
    0.56
     ſche
    0.51
     AssemblyCulture
    0.50
    InitVars
    0.50
     CreateTagHelper
    0.50
    richTextPanel
    0.48
     gynhyrchwyd
    0.46
    fjspx
    0.45
     Infórmanos
    0.45
    setVerticalGroup
    0.44
    Activations Density 0.362%

    No Known Activations