© 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. 20816
    Prev
    Next
    INDEX
    Explanations

    references and terms related to cultural and regional groups

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

    Mai, bal, j, Nasi

    np_acts-logits-general · gemini-2.5-flash-lite

    specialized or foreign terms—often hyphenated/reduplicated—and their in-text definitions or glosses signaled by quotes or parentheses.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     Cæsar
    -0.73
     Majefty
    -0.63
     مشين
    -0.61
    IntoConstraints
    -0.59
    存于互联网档案馆
    -0.59
     Inſ
    -0.57
     Perfon
    -0.56
    SequentialGroup
    -0.53
     Eſ
    -0.53
     Efq
    -0.52
    POSITIVE LOGITS
    :✨
    0.47
    ########.
    0.45
    pronounced
    0.38
     manualmente
    0.38
    UNESCO
    0.37
    libft
    0.37
     polvo
    0.36
    と呼ばれる
    0.36
     traditionally
    0.36
    commonly
    0.35
    Activations Density 0.040%

    No Known Activations