© 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. 110647
    Prev
    Next
    INDEX
    Explanations

    references to protective mechanisms or objects

    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
     shield
    -2.17
    shield
    -2.03
     Shield
    -1.98
     shields
    -1.92
    Shield
    -1.84
    shields
    -1.48
     Shields
    -1.48
     SHIELD
    -1.42
    hield
    -1.39
     shielding
    -1.38
    POSITIVE LOGITS
     Junta
    0.35
     Ier
    0.32
     spiaggia
    0.32
     Embaj
    0.31
     rouge
    0.31
     Packing
    0.30
    packing
    0.30
     ledit
    0.30
     conoc
    0.30
     Geophys
    0.29
    Activations Density 0.001%

    No Known Activations