© 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. 9-GEMMASCOPE-RES-131K
    11. 5399
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Xing" and its variations

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

    Xing names and star, week, film

    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
     useCallback
    -0.45
    TargetApi
    -0.45
    orteur
    -0.43
    IUrlHelper
    -0.43
     newOwner
    -0.40
     UILabel
    -0.40
    nonatomic
    -0.40
    ypep
    -0.40
    Dichloro
    -0.39
    opcao
    -0.39
    POSITIVE LOGITS
    Xing
    2.11
     Xing
    2.09
    xing
    1.94
     xing
    1.94
    兴
    1.24
    星
    1.23
    興
    1.13
     星
    1.12
    星の
    0.92
     興
    0.86
    Activations Density 0.004%

    No Known Activations