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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 109406
    Prev
    Next
    INDEX
    Explanations

    terms related to Indigenous peoples and cultures

    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
     Aboriginal
    -1.34
     Aborig
    -0.93
     aboriginal
    -0.91
     Native
    -0.54
     Indigenous
    -0.52
     Maori
    -0.51
     Māori
    -0.47
    Ab
    -0.47
    Indigenous
    -0.44
     indigenous
    -0.42
    POSITIVE LOGITS
    ValueStyle
    0.82
    IntoConstraints
    0.75
    存于互联网档案馆
    0.72
    URLException
    0.71
    findpost
    0.67
    migrationBuilder
    0.65
    bootstrapcdn
    0.65
     MainAxisSize
    0.63
    AnchorStyles
    0.63
    GOTREF
    0.63
    Activations Density 0.000%

    No Known Activations