© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110535
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a source or origin of nutrients or benefits

    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
     source
    -0.61
     sources
    -0.60
     fontes
    -0.52
    แหล่ง
    -0.49
     Source
    -0.49
     Sources
    -0.49
    Източници
    -0.48
    riwal
    -0.48
    source
    -0.48
    sources
    -0.47
    POSITIVE LOGITS
     nakalista
    0.62
    AnchorStyles
    0.56
    ArrowToggle
    0.54
    сылкі
    0.50
    Tikang
    0.50
    الدراسه
    0.48
    ROIT
    0.48
    __':
    0.47
    AddTagHelper
    0.47
     سكانية
    0.47
    Activations Density 0.007%

    No Known Activations