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. 109787
    Prev
    Next
    INDEX
    Explanations

    references to pensions and pension plans

    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
     pension
    -1.94
     Pension
    -1.70
    Pension
    -1.60
     pensions
    -1.56
    pension
    -1.51
     Pensions
    -1.34
     pensioners
    -1.13
     пен
    -0.94
     pensi
    -0.81
     retire
    -0.81
    POSITIVE LOGITS
    UnusedPrivate
    0.71
    IsMutable
    0.59
    findpost
    0.57
     ComVisible
    0.56
    LookAnd
    0.54
    RegressionTest
    0.54
     endblock
    0.53
    __":
    
    0.53
    出版年
    0.52
    onomía
    0.52
    Activations Density 0.001%

    No Known Activations