© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 3593
    Prev
    Next
    INDEX
    Explanations

    Arabic characters and symbols, indicating a focus on texts in the Arabic language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.83
     Paglinawan
    -0.74
    nemouth
    -0.68
    ViewFeatures
    -0.66
    ználat
    -0.62
    ترة
    -0.61
    fromLTRB
    -0.61
     chi̍t
    -0.61
     הן
    -0.60
    focusable
    -0.59
    POSITIVE LOGITS
     يتيمه
    0.80
    LEGGI
    0.57
     OFDb
    0.56
    ک
    0.53
    ص
    0.53
     setae
    0.52
     ب
    0.52
    ?}",
    0.52
    ?,?,
    0.52
    انگلیسی
    0.52
    Activations Density 0.045%

    No Known Activations