© 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. 14159
    Prev
    Next
    INDEX
    Explanations

    discussions about moral and ethical controversies, particularly those involving societal judgments and personal accountability

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

    followed by prepositions or conjunctions

    np_acts-logits-general · gemini-2.0-flash

    specific API endpoints

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

    politically charged commentary about public figures, governments, and legal proceedings, especially when discussing controversy, accusations, or opposition.

    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-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
     Pemain
    -0.34
    ServiceClient
    -0.31
     Waz
    -0.30
     définir
    -0.30
    Produk
    -0.29
     Perusahaan
    -0.29
    problemas
    -0.28
     previsão
    -0.28
     proteção
    -0.28
    XmlEnum
    -0.28
    POSITIVE LOGITS
    enderror
    0.94
     ویکی‌پدی
    0.72
     EconPapers
    0.65
     FetchType
    0.65
    SequentialGroup
    0.64
    LookAnd
    0.61
    ImageContext
    0.60
    >//
    0.60
    usercontent
    0.60
    SharedDtor
    0.59
    Activations Density 0.957%

    No Known Activations