© 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 - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 55127
    Prev
    Next
    INDEX
    Explanations

    Java method calls related to user interface actions and threading

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

    user input prefixes

    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
    expandindo
    -0.52
    ExtendWith
    -0.50
    RunWith
    -0.49
    SerializedName
    -0.48
    __":
    
    -0.48
     EconPapers
    -0.47
     OMITBAD
    -0.47
    ]")]
    -0.46
    __':
    
    -0.46
     ExecuteAsync
    -0.45
    POSITIVE LOGITS
    JOptionPane
    2.05
     JOptionPane
    1.37
     defaultstate
    0.82
    MessageBox
    0.66
    OptionPane
    0.64
    QMessageBox
    0.59
    AlertDialog
    0.52
     parallelogram
    0.52
     AlertDialog
    0.52
     OCLC
    0.51
    Activations Density 0.000%

    No Known Activations