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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 8310
    Prev
    Next
    INDEX
    Explanations

    references to debt and indebtedness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schwier
    -0.35
    ronpa
    -0.35
    googleapis
    -0.34
     inconnu
    -0.32
    lindungan
    -0.31
    ẳng
    -0.31
    탤
    -0.31
    łac
    -0.31
     Beobachtung
    -0.31
     Gemü
    -0.30
    POSITIVE LOGITS
     autorytatywna
    0.89
    Personensuche
    0.87
     debt
    0.84
     Debt
    0.75
    Debt
    0.72
    debt
    0.71
     trading
    0.66
    Trail
    0.65
    Trading
    0.63
    :✨
    0.63
    Activations Density 0.073%

    No Known Activations