© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109367
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "part" or 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
     части
    -0.97
     часть
    -0.66
     частью
    -0.56
    части
    -0.55
     część
    -0.54
    的一部分
    -0.54
     części
    -0.54
     části
    -0.53
     časti
    -0.49
    一部分
    -0.49
    POSITIVE LOGITS
    TagMode
    0.67
    oa̍t
    0.47
     arşivlendi
    0.45
    //};
    0.44
     الرياضيه
    0.43
    }));
    
    0.43
    '])){
    
    0.42
    ']))
    
    0.41
     []).
    0.41
    '});
    0.40
    Activations Density 0.002%

    No Known Activations