© 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. 5625
    Prev
    Next
    INDEX
    Explanations

    function calls and associated method chains in code

    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
     CreateTagHelper
    -0.74
    dafx
    -0.52
    存于互联网档案馆
    -0.52
     Савезне
    -0.51
    хьтан
    -0.50
    windowFixed
    -0.49
    fjspx
    -0.49
    UrlResolution
    -0.48
     gyhoeddwyd
    -0.48
     ligiloj
    -0.47
    POSITIVE LOGITS
    toString
    1.16
     toString
    1.00
    ToString
    0.86
     ToString
    0.75
     nói
    0.46
     said
    0.45
     saying
    0.44
    toLocale
    0.42
     Say
    0.42
    String
    0.42
    Activations Density 0.181%

    No Known Activations