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-2-2B
    4. MLP Out - 65k
    5. 18-GEMMASCOPE-MLP-65K
    6. 18
    Prev
    Next
    INDEX
    Explanations

    references to a specific medication and its dosing in a clinical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.18.hook_mlp_out
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wicidata
    -0.45
     scaricare
    -0.44
    httphttps
    -0.44
    hält
    -0.44
    __':
    
    -0.42
    __":
    -0.42
    یشن
    -0.41
    torie
    -0.41
    excel
    -0.40
    ZIE
    -0.40
    POSITIVE LOGITS
    Autoritní
    0.75
    AnchorStyles
    0.75
    TagMode
    0.72
    MessageTagHelper
    0.71
    queryInterface
    0.67
    
    0.67
    transQ
    0.66
    yntaxException
    0.66
    SequentialGroup
    0.65
    ’;
    0.62
    Activations Density 0.477%

    No Known Activations