Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 21622
    Prev
    Next
    INDEX
    Explanations

    user interface elements in Java code

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

    GUI 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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    RegressionTest
    -0.53
    ngrx
    -0.47
     BoxFit
    -0.46
    intios
    -0.44
    pstmt
    -0.43
    lcc
    -0.38
    clientX
    -0.37
    HomeAsUp
    -0.36
    mousemove
    -0.36
    toHaveBeen
    -0.36
    POSITIVE LOGITS
     JButton
    0.73
     JTextField
    0.68
     JLabel
    0.67
    InputTagHelper
    0.60
    AnimationsModule
    0.59
     JMenuItem
    0.57
     AssemblyCompany
    0.54
     AssemblyTitle
    0.54
     QLabel
    0.52
    setViewportView
    0.51
    Activations Density 0.003%

    No Known Activations