© 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. 25-GEMMASCOPE-RES-16K
    6. 2719
    Prev
    Next
    INDEX
    Explanations

    references to economic strategies and data related to GDP and international trade

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tető
    -0.51
    uride
    -0.49
    refront
    -0.48
     Lyle
    -0.45
     Langmuir
    -0.45
    Segoe
    -0.45
     Lay
    -0.45
    Protocols
    -0.44
    ObjectMeta
    -0.44
     revend
    -0.44
    POSITIVE LOGITS
     GDP
    0.74
     Gross
    0.73
     gross
    0.68
    Gross
    0.66
    GDP
    0.66
     GNP
    0.64
     Merchandise
    0.63
     (%
    0.62
     GROSS
    0.62
     autorytatywna
    0.62
    Activations Density 0.201%

    No Known Activations