© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 15401
    Prev
    Next
    INDEX
    Explanations

    specific Turkish words and phrases, often related to cultural or local references

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

    Turkish words or phrases

    np_acts-logits-general · gemini-2.0-flash

    Turkish language and culture

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kılıf
    -0.86
     küpe
    -0.85
     bileklik
    -0.76
     kağıdı
    -0.76
     vektör
    -0.68
     yüzük
    -0.68
     väli
    -0.66
     gömlek
    -0.66
     desenli
    -0.65
     yağı
    -0.65
    POSITIVE LOGITS
     fieldNum
    0.93
    #+#
    0.89
    sizeCache
    0.89
    +#+
    0.81
     resourceCulture
    0.80
     للمعارف
    0.78
    TypedDataSet
    0.77
     linkovi
    0.76
    hyrchwyd
    0.75
     autorytatywna
    0.74
    Activations Density 0.015%

    No Known Activations