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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. MLP Out - 16k
    5. 1-GEMMASCOPE-MLP-16K
    6. 8926
    Prev
    Next
    INDEX
    Explanations

    terms related to spas and wellness services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     spare
    -1.05
     Spare
    -1.02
    Spa
    -1.00
     Spa
    -1.00
     spa
    -0.97
    spa
    -0.94
    spare
    -0.92
    Spare
    -0.91
     SPA
    -0.90
     CreateTagHelper
    -0.88
    POSITIVE LOGITS
    GNUC
    0.62
    ]){
    
    0.56
    })`
    0.54
    \{\\
    0.51
    ruz
    0.50
     numerus
    0.50
    =?";
    0.49
    }';
    0.49
    manes
    0.48
    ]";
    0.48
    Activations Density 0.278%

    No Known Activations