© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4559
    Prev
    Next
    INDEX
    Explanations

    code-related terms and elements indicative of software implementation

    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
     ſta
    -0.81
     auroit
    -0.79
     étoit
    -0.77
     feroit
    -0.74
     pouvoit
    -0.73
     quæ
    -0.73
     enfans
    -0.70
     avoient
    -0.64
     eſſ
    -0.62
     ſec
    -0.60
    POSITIVE LOGITS
    tagHelperRunner
    0.72
    Personendaten
    0.66
     oof
    0.62
    GEBURTSDATUM
    0.62
     liek
    0.60
    fom
    0.59
     للاسماء
    0.59
    ScopeManager
    0.58
     fro
    0.58
     wither
    0.58
    Activations Density 1.114%

    No Known Activations