© 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. 86677
    Prev
    Next
    INDEX
    Explanations

    references to existential questions or statements

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

    What are you

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

    tokens that begin a sentence or turn (sentence- or turn-initial tokens, often capitalized).

    oai_token-act-pair · gpt-5-miniTriggered 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
     незавершена
    -0.41
    ValueStyle
    -0.41
     Kecil
    -0.39
    ніципа
    -0.38
     Trabalho
    -0.36
     Nieren
    -0.35
    ьажоргаш
    -0.34
     conmigo
    -0.34
     adelant
    -0.34
     lector
    -0.33
    POSITIVE LOGITS
     ſind
    0.52
    retweeted
    0.49
     ſch
    0.49
     NSCoder
    0.48
    setVerticalGroup
    0.47
    extAlignment
    0.47
    styleable
    0.47
    Capítulo
    0.46
    ipelago
    0.46
     eſſ
    0.46
    Activations Density 0.000%

    No Known Activations