© 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. 31-GEMMASCOPE-RES-131K
    6. 65205
    Prev
    Next
    INDEX
    Explanations

    references to AngularJS controllers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pinulongan
    -0.52
     незавершена
    -0.51
    utilisons
    -0.48
    脚注の使い方
    -0.47
    GraphicsUnit
    -0.47
    getSystemService
    -0.45
     Мексичка
    -0.45
     cherchés
    -0.45
    Tikang
    -0.43
     OMITBAD
    -0.42
    POSITIVE LOGITS
    RestController
    0.98
    ControllerAdvice
    0.64
    ApiController
    0.57
    XmlAccessType
    0.49
    oredCriteria
    0.48
    controller
    0.48
     houſe
    0.47
    SourceChecksum
    0.47
     Controller
    0.46
    urlpatterns
    0.46
    Activations Density 0.000%

    No Known Activations