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-2-9B
    4. Residual Stream - 16k
    5. 35-GEMMASCOPE-RES-16K
    6. 7087
    Prev
    Next
    INDEX
    Explanations

    financial terms related to debt and economic burdens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pud
    -0.41
     CommonModule
    -0.40
    phosa
    -0.38
    xase
    -0.38
    pud
    -0.37
    igil
    -0.36
     kij
    -0.35
     pl
    -0.35
    basti
    -0.34
     goose
    -0.34
    POSITIVE LOGITS
     debt
    2.50
     debts
    2.19
     Debt
    2.05
    debt
    2.03
    Debt
    2.00
     indebtedness
    1.86
     deuda
    1.83
     indebted
    1.78
     owe
    1.70
     owes
    1.66
    Activations Density 0.415%

    No Known Activations