© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11153
    Prev
    Next
    INDEX
    Explanations

    components related to user interface elements in programming

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

    Code snippets related to UI elements

    np_acts-logits-general · gemini-2.0-flash

    UI layout and components

    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
    
    -0.71
     المعيارى
    -0.66
     nakalista
    -0.60
    SpringBootTest
    -0.58
    IUrlHelper
    -0.57
    Chham
    -0.57
     ſind
    -0.57
     Roskov
    -0.56
     StatefulWidget
    -0.56
     AssemblyCompany
    -0.56
    POSITIVE LOGITS
    WebElementEntity
    0.35
    Présentation
    0.35
     arranged
    0.33
    aménagement
    0.33
    みましょう
    0.32
     layout
    0.31
     susun
    0.31
     flooring
    0.31
    Handlung
    0.30
    INSTALLED
    0.30
    Activations Density 0.148%

    No Known Activations