© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 107591
    Prev
    Next
    INDEX
    Explanations

    references to programming controllers and the structure of code within a software context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Infórmanos
    -0.55
    interopRequire
    -0.46
    RegressionTest
    -0.43
    XMLSchema
    -0.42
     dAtA
    -0.42
    GraphicsUnit
    -0.40
    зможно
    -0.38
     heapq
    -0.38
    новниш
    -0.38
    copg
    -0.37
    POSITIVE LOGITS
    Controller
    0.81
     ControllerBase
    0.81
     Controller
    0.64
    Controllers
    0.63
    ViewFeatures
    0.63
    ControllerTest
    0.60
    SequentialGroup
    0.57
    controller
    0.56
    BaseController
    0.53
     UserController
    0.53
    Activations Density 0.000%

    No Known Activations