© 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. 60430
    Prev
    Next
    INDEX
    Explanations

    terms related to "tur" or "Turkish" context, particularly in relation to turbid conditions or characters

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

    tur prefix followed by diverse words

    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
     bookId
    -0.53
     Classe
    -0.49
    Classe
    -0.48
    manda
    -0.46
    命中
    -0.46
    <h5>
    -0.45
    BibitemShut
    -0.45
     Sense
    -0.45
    bookId
    -0.44
    sense
    -0.44
    POSITIVE LOGITS
     Tur
    2.22
    Tur
    2.03
     tur
    2.02
    tur
    1.83
     TUR
    1.76
    TUR
    1.57
    Turb
    1.21
     Turf
    1.16
     Тур
    1.12
    Тур
    1.10
    Activations Density 0.007%

    No Known Activations