© 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. 654
    Prev
    Next
    INDEX
    Explanations

    elements and attributes related to language in code or data structures

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

    Language, locale, and translation

    np_acts-logits-general · gemini-2.0-flash

    language and locale settings

    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
    findpost
    -0.69
    ReusableCell
    -0.65
     cref
    -0.63
     JpaRepository
    -0.62
    RenderAtEndOf
    -0.61
     GenerationType
    -0.55
    VersionUID
    -0.55
    CloseOperation
    -0.54
    WriteTagHelper
    -0.53
    parsedMessage
    -0.53
    POSITIVE LOGITS
    LOCALE
    0.68
     Languages
    0.65
    Locale
    0.62
     languages
    0.60
     idiomas
    0.58
    languages
    0.56
     Locale
    0.55
     countries
    0.54
     Language
    0.54
    locale
    0.54
    Activations Density 0.266%

    No Known Activations