© 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. 5683
    Prev
    Next
    INDEX
    Explanations

    programming and software-related identifiers, particularly in code and documentation contexts

    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
     InputDecoration
    -0.75
    yntaxException
    -0.65
    WriteTagHelper
    -0.61
    WithIOException
    -0.60
     allAfrica
    -0.59
    Aiheesta
    -0.58
    ]=>
    -0.58
    atchewan
    -0.58
    therosclerosis
    -0.58
    cruz
    -0.57
    POSITIVE LOGITS
     للمعارف
    0.35
     vyp
    0.33
     fact
    0.28
     cré
    0.27
     Voll
    0.27
     pen
    0.26
     guard
    0.26
     bit
    0.26
     Tor
    0.25
    满
    0.25
    Activations Density 0.251%

    No Known Activations