© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4688
    Prev
    Next
    INDEX
    Explanations

    text in the Kannada language

    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
    hdys
    -0.44
    IntoConstraints
    -0.43
    Życiorys
    -0.43
    mybatisplus
    -0.39
     MessageBoxIcon
    -0.37
    quiagem
    -0.36
     AssemblyCulture
    -0.35
     samfun
    -0.35
     quelcon
    -0.34
    addSubview
    -0.33
    POSITIVE LOGITS
     Karnataka
    0.82
     Mysore
    0.79
     Kannada
    0.76
    Mys
    0.75
     Mys
    0.75
     Bengaluru
    0.74
     Bangalore
    0.69
    Karn
    0.64
     Vok
    0.59
     mys
    0.58
    Activations Density 0.181%

    No Known Activations