© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 110112
    Prev
    Next
    INDEX
    Explanations

    references to the second-person possessive pronoun "your" and its variations

    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
    Your
    -0.88
    your
    -0.85
     Your
    -0.84
    YOUR
    -0.79
     YOUR
    -0.75
     your
    -0.69
    Ваш
    -0.60
    你的
    -0.59
    あなたの
    -0.55
     Ваш
    -0.53
    POSITIVE LOGITS
     initComponents
    0.68
    oneofs
    0.59
    
    0.59
    OGND
    0.58
    addContainerGap
    0.57
    ValueStyle
    0.56
     חיצוניים
    0.54
    +#+#
    0.52
    ########.
    0.49
    Diweddarwch
    0.49
    Activations Density 0.007%

    No Known Activations