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. 5-GEMMASCOPE-RES-16K
    6. 12781
    Prev
    Next
    INDEX
    Explanations

    terms and references related to finance and financial roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.84
     AssemblyCulture
    -0.72
    TabStop
    -0.70
     Epp
    -0.70
     Symptom
    -0.69
     Atwood
    -0.68
    jerk
    -0.68
    ContentAlignment
    -0.68
     goat
    -0.68
    beads
    -0.67
    POSITIVE LOGITS
     finance
    2.28
     Finance
    2.08
    Finance
    1.96
    finance
    1.96
     FINANCE
    1.91
     finan
    1.63
     financing
    1.61
     finances
    1.57
     financed
    1.42
     finans
    1.40
    Activations Density 0.069%

    No Known Activations