© 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. 108703
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation that separate sections or denote emphasis in 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
     CreateTagHelper
    -0.80
    OGND
    -0.77
    ValueStyle
    -0.76
    RenderAtEndOf
    -0.74
     ainfi
    -0.73
     الحره
    -0.72
     Wiktionnaire
    -0.71
     desmotivaciones
    -0.70
     beginnetje
    -0.69
    IntoConstraints
    -0.68
    POSITIVE LOGITS
    ↵↵
    0.42
     ag
    0.41
    <eos>
    0.40
     pur
    0.38
    lie
    0.38
    va
    0.37
    ble
    0.37
    eng
    0.37
    lare
    0.36
    alima
    0.36
    Activations Density 0.135%

    No Known Activations