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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 15-GEMMASCOPE-RES-16K
    6. 12880
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to budgets and financial planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.90
     autorytatywna
    -0.88
    saraba
    -0.81
     Lees
    -0.81
     CWE
    -0.81
    lwjgl
    -0.80
     '',
    
    -0.79
     fibrillation
    -0.79
     '{@
    -0.75
     Rowling
    -0.74
    POSITIVE LOGITS
     budget
    1.45
     budgets
    1.37
     Budget
    1.34
    Budget
    1.24
     BUDGET
    1.22
    budget
    1.22
    BUDGET
    1.18
     Budgets
    1.14
     budgeting
    1.02
     Budgeting
    0.98
    Activations Density 0.060%

    No Known Activations