© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 133
    Prev
    Next
    INDEX
    Explanations

    instances of the word "ask" and related phrases involving inquiries and questions

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

    Texts containing the word "ask"

    np_acts-logits-general · gemini-2.0-flash

    asking specific questions

    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
    ViewInit
    -0.61
     AssemblyVersion
    -0.50
     LocalDateTime
    -0.46
    bootstrapcdn
    -0.45
    ChildScrollView
    -0.45
     ویکی‌پدی
    -0.45
    ########.
    -0.44
     McNally
    -0.44
    migrationBuilder
    -0.44
    StoryboardSegue
    -0.43
    POSITIVE LOGITS
     ask
    1.27
     Ask
    1.19
     ASK
    1.15
    Ask
    1.09
     asked
    1.09
     asks
    1.08
     asking
    1.02
    ASK
    1.02
    ask
    1.00
     Asking
    1.00
    Activations Density 0.065%

    No Known Activations