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. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 9785
    Prev
    Next
    INDEX
    Explanations

    references to financial capital and its management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     quæ
    -0.76
     africains
    -0.71
     sandero
    -0.68
       
    -0.66
     âgé
    -0.66
     étrangères
    -0.66
     auroit
    -0.64
     déploy
    -0.64
     eût
    -0.62
     duquel
    -0.61
    POSITIVE LOGITS
     Capital
    1.44
     capital
    1.39
    Capital
    1.30
    capital
    1.21
     CAPITAL
    1.21
    CAPITAL
    0.94
     availability
    0.82
     BoxDecoration
    0.82
     Availability
    0.79
     capitol
    0.78
    Activations Density 0.181%

    No Known Activations