© 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-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 6600
    Prev
    Next
    INDEX
    Explanations

    specific characters or letters in multiple languages, especially Arabic and English

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     informée
    -0.49
    enderror
    -0.44
     المعرف
    -0.44
     wireType
    -0.40
    couvrez
    -0.39
    RegressionTest
    -0.38
    couvrir
    -0.37
    rahmen
    -0.36
    appliquer
    -0.35
    xrTableCell
    -0.35
    POSITIVE LOGITS
     OFDb
    0.50
    setVerticalGroup
    0.40
    Tracce
    0.40
    aspect
    0.40
    сылкі
    0.39
    GEBURTSDATUM
    0.39
     circunstancia
    0.38
    Décès
    0.38
    antMatchers
    0.38
    CloseOperation
    0.36
    Activations Density 0.250%

    No Known Activations