© 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. 20-GEMMASCOPE-RES-16K
    6. 8800
    Prev
    Next
    INDEX
    Explanations

    terms related to sustainability and economic development initiatives

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

    economic progress/development and sustainability

    np_acts-logits-general · gemini-2.0-flash

    sustainable economic development and prosperity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ptest
    -0.50
    hdys
    -0.45
    UnsafeEnabled
    -0.44
     anonim
    -0.43
     refresher
    -0.42
    MockMvc
    -0.42
     trucos
    -0.40
    zin
    -0.40
    tene
    -0.39
     dibanding
    -0.39
    POSITIVE LOGITS
     prosperity
    0.77
     FontWeight
    0.76
     Sustainable
    0.74
     sustainable
    0.73
     SDGs
    0.73
    perity
    0.71
     poverty
    0.70
     transformation
    0.70
     Prosperity
    0.69
     prosperous
    0.68
    Activations Density 0.104%

    No Known Activations