© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 1740
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial transactions, funding, and the redistribution of money

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.49
    ettbewer
    -0.49
     كومونز
    -0.46
    Referanser
    -0.45
     expédié
    -0.45
     Establishment
    -0.44
    AutoScale
    -0.44
     lij
    -0.43
     cameo
    -0.43
    oader
    -0.43
    POSITIVE LOGITS
     spent
    0.81
     Spent
    0.76
     reinvest
    0.75
    spend
    0.72
    spent
    0.70
     spend
    0.70
     squander
    0.69
     earmarked
    0.69
     dépens
    0.68
    Spending
    0.67
    Activations Density 0.321%

    No Known Activations