© 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. 110420
    Prev
    Next
    INDEX
    Explanations

    technical terms related to circuit components and their characteristics

    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
    tagHelperRunner
    -0.49
     initComponents
    -0.48
     ModelExpression
    -0.47
    InSection
    -0.46
     Touchable
    -0.43
     RouterModule
    -0.43
     imobili
    -0.42
    ftagPool
    -0.42
     Neu
    -0.42
    oredCriteria
    -0.42
    POSITIVE LOGITS
    AISSEE
    0.47
    UserScript
    0.46
    évaluateur
    0.41
    windowFixed
    0.37
    fycat
    0.37
    TagMode
    0.36
    TypedDataSet
    0.35
    ↕
    0.35
     kurie
    0.35
     todėl
    0.34
    Activations Density 0.137%

    No Known Activations