© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 13282
    Prev
    Next
    INDEX
    Explanations

    concepts related to environmental economics and sustainability

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     يتيمه
    -0.73
    口
    -0.50
     HasFactory
    -0.49
    面倒
    -0.44
     gawas
    -0.43
    COMPLE
    -0.42
    pośred
    -0.42
    dollis
    -0.42
     décontract
    -0.41
     AssemblyVersion
    -0.40
    POSITIVE LOGITS
     Earth
    0.53
     ecosystems
    0.52
     earth
    0.48
     ecological
    0.48
     biodiversity
    0.47
     nature
    0.47
     OMITBAD
    0.47
     conservation
    0.47
     sustainable
    0.46
     unsustainable
    0.45
    Activations Density 0.138%

    No Known Activations