© 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
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11289
    Prev
    Next
    INDEX
    Explanations

    Java GUI component management actions, particularly related to adding and organizing panels and layouts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    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
     AssemblyCompany
    -0.68
     насељу
    -0.64
    #+#
    -0.60
    
    -0.60
    ⤹
    -0.59
    AsUp
    -0.59
     ControllerBase
    -0.57
    WarningLevel
    -0.56
    InjectMocks
    -0.54
    bootstrapcdn
    -0.54
    POSITIVE LOGITS
    GroupLayout
    0.98
    setVerticalGroup
    0.80
    setHorizontal
    0.79
    BagLayout
    0.66
    awtextra
    0.66
    IntoConstraints
    0.54
    BagConstraints
    0.47
    makeConstraints
    0.46
    BoxLayout
    0.46
     nahilalakip
    0.43
    Activations Density 0.010%

    No Known Activations