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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128410
    Prev
    Next
    INDEX
    Explanations

    the method definition for "onCreate" in an Android application

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

    android onCreate method

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     bomb
    -0.28
     sent
    -0.28
    boolean
    -0.27
     worm
    -0.27
    saveData
    -0.27
     label
    -0.27
    getDb
    -0.26
     bây
    -0.26
    )]
    -0.26
    jemahan
    -0.26
    POSITIVE LOGITS
     onCreate
    4.78
    onCreate
    2.42
     onCreateView
    2.02
     viewDidLoad
    1.70
    viewDidLoad
    1.34
    MemoryWarning
    1.30
     onBind
    1.29
    onViewCreated
    1.28
    __':
    1.23
     onDestroy
    1.20
    Activations Density 0.000%

    No Known Activations