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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109726
    Prev
    Next
    INDEX
    Explanations

    specific scientific or technical terms related to human and animal biology

    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
     human
    -0.73
    Human
    -0.69
    human
    -0.68
     humana
    -0.68
     humanas
    -0.63
     menschlichen
    -0.63
     humanos
    -0.62
     HUMAN
    -0.62
    HUMAN
    -0.61
     menschliche
    -0.61
    POSITIVE LOGITS
     تضيفلها
    0.51
    
    0.50
    EndContext
    0.46
    SBATCH
    0.44
    Geplaatst
    0.44
    colnshire
    0.43
    PLANATION
    0.43
    familiar
    0.40
     familiar
    0.40
    脚注の使い方
    0.40
    Activations Density 0.027%

    No Known Activations