© 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. 4461
    Prev
    Next
    INDEX
    Explanations

    technical terms related to errors and programming concepts, particularly in API 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
    httphttps
    -0.37
     iNdEx
    -0.32
    ="@+
    -0.30
    getWriter
    -0.28
     cellspacing
    -0.27
    dent
    -0.26
    WritableDatabase
    -0.26
     dedu
    -0.26
     Decks
    -0.26
     Tribut
    -0.25
    POSITIVE LOGITS
     domain
    3.31
     Domain
    3.05
    Domain
    2.94
     domains
    2.86
    domain
    2.86
     dom
    2.80
     Dom
    2.77
     DOMAIN
    2.72
    Dom
    2.67
     Domains
    2.66
    Activations Density 0.933%

    No Known Activations