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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14751
    Prev
    Next
    INDEX
    Explanations

    phrases related to financial resource management and economic consequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.85
     Roskov
    -0.78
    ScopeManager
    -0.73
    enumi
    -0.68
     AssemblyProduct
    -0.65
    StoreMessageInfo
    -0.64
    AndEndTag
    -0.64
     يتيمه
    -0.62
     مشين
    -0.61
     surla
    -0.60
    POSITIVE LOGITS
     majority
    2.19
     sebagian
    2.09
    majority
    1.91
    大部分
    1.87
     some
    1.70
    Majority
    1.67
     Majority
    1.62
    大半
    1.61
     mayoría
    1.60
     plupart
    1.58
    Activations Density 1.076%

    No Known Activations