© 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. 110329
    Prev
    Next
    INDEX
    Explanations

    instances of the word "knows" in various contexts

    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
     knows
    -1.13
    knows
    -1.00
     знает
    -0.71
     Knows
    -0.65
     sabe
    -0.59
     knew
    -0.58
     conoce
    -0.57
     kennt
    -0.55
    Knows
    -0.54
    knew
    -0.53
    POSITIVE LOGITS
     Савезне
    0.65
    +#+#
    0.63
    ſehen
    0.62
    ScopeManager
    0.59
    存于互联网档案馆
    0.56
     utafitiHapana
    0.55
    lofen
    0.54
    ForValue
    0.54
    \{\\
    0.54
    PerformLayout
    0.54
    Activations Density 0.003%

    No Known Activations