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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 44980
    Prev
    Next
    INDEX
    Explanations

    references to a specific language or coding framework, likely related to "zh" indicating Chinese or a related coding context

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

    zh names ending in ansky or ukov

    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
     Wilcox
    -0.45
    by
    -0.43
    ovon
    -0.39
    are
    -0.38
    return
    -0.38
    椒
    -0.38
    UrlResolution
    -0.37
    ا
    -0.37
    ksiä
    -0.37
    copy
    -0.37
    POSITIVE LOGITS
    zh
    2.09
     zh
    1.77
     Zh
    1.38
    Zh
    1.34
    ZH
    1.30
     ZH
    1.12
    ChildScrollView
    0.80
    Ж
    0.68
    izh
    0.66
     defaultstate
    0.64
    Activations Density 0.006%

    No Known Activations