© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 726
    Prev
    Next
    INDEX
    Explanations

    mathematical notation and symbols used in formal expressions

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

    Expressions with parentheses and symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions involving parentheses

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    intenant
    -0.32
     eventId
    -0.31
     urme
    -0.30
    httphttps
    -0.30
     säkert
    -0.30
     malheur
    -0.29
     selera
    -0.28
     définiti
    -0.28
     getRule
    -0.28
    vikling
    -0.28
    POSITIVE LOGITS
     nahilalakip
    0.71
     الحره
    0.68
    ]")]
    0.66
     мәкал
    0.64
    wixt
    0.64
     فريبيس
    0.60
    colhead
    0.59
    ۜ
    0.58
    ✨:
    0.56
    QMetaType
    0.56
    Activations Density 0.980%

    No Known Activations