Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109903
    Prev
    Next
    INDEX
    Explanations

    references to video game characters and themes

    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
     ter
    -0.27
    []{"
    -0.25
     j
    -0.24
     
    -0.24
     ujarnya
    -0.23
    j
    -0.23
    justifyContent
    -0.23
    ็ง
    -0.23
     posteriores
    -0.22
    enerbahçe
    -0.22
    POSITIVE LOGITS
    rungsseite
    0.91
    +#+#
    0.86
     estekak
    0.85
     resourceCulture
    0.81
    :✨
    0.81
    ंदीखरीदारी
    0.79
    transQ
    0.74
    참고
    0.73
    Autoritní
    0.72
     ujednoznacz
    0.71
    Activations Density 0.248%

    No Known Activations