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

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15513
    Prev
    Next
    INDEX
    Explanations

    phrases related to humanitarian efforts and community support

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Positive feedback for someone's efforts

    np_acts-logits-general · gemini-2.0-flash

    work and efforts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kháu
    -0.62
     NgModule
    -0.54
    RegressionTest
    -0.52
     חיצוניים
    -0.49
     jumping
    -0.49
    Viited
    -0.48
     שוליים
    -0.47
    DIRS
    -0.47
    databind
    -0.47
    toHave
    -0.46
    POSITIVE LOGITS
     work
    1.39
     efforts
    1.23
    efforts
    1.07
    work
    1.05
     Efforts
    1.00
     trabalho
    0.98
    工作
    0.96
     lavoro
    0.95
     trabalhos
    0.94
     работы
    0.94
    Activations Density 0.121%

    No Known Activations