© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 121348
    Prev
    Next
    INDEX
    Explanations

    elements related to economic trends and policies

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

    court rulings and governments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     bin
    -0.30
     gap
    -0.30
     dök
    -0.30
     eux
    -0.29
     eventually
    -0.28
     exotic
    -0.28
    大量的
    -0.28
     ad
    -0.26
     pan
    -0.26
     precursor
    -0.26
    POSITIVE LOGITS
     يتيمه
    0.88
     propOrder
    0.82
     snippetHide
    0.77
     EconPapers
    0.71
     disambiguazione
    0.69
    PerformLayout
    0.69
    WebElementEntity
    0.69
     nakalista
    0.69
    Personendaten
    0.67
    opsida
    0.66
    Activations Density 0.024%

    No Known Activations