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. 4-GEMMASCOPE-RES-16K
    6. 12301
    Prev
    Next
    INDEX
    Explanations

    repeated mentions of the term "money."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    :✨
    -0.85
     CreateTagHelper
    -0.84
    rzost
    -0.82
    Goat
    -0.81
    ؤلاء
    -0.80
     कृपया
    -0.79
    ilant
    -0.77
    évêque
    -0.76
    GHIJKLM
    -0.76
     Veld
    -0.74
    POSITIVE LOGITS
     money
    2.47
    money
    2.20
     Money
    2.17
    Money
    2.14
     MONEY
    2.04
    MONEY
    1.88
     dinero
    1.61
     dinheiro
    1.49
     moneys
    1.41
     Geld
    1.39
    Activations Density 0.050%

    No Known Activations