© 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. 31-GEMMASCOPE-RES-16K
    11. 11130
    Prev
    Next
    INDEX
    Explanations

    elements related to resource management and subscription-based services in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    parameter names and variable identifiers in code, particularly those with compound names like "resourceGroupName" and "subscriptionId".

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     still
    -0.90
     yet
    -0.85
     ainda
    -0.77
    yet
    -0.74
     todavía
    -0.73
    still
    -0.72
     aún
    -0.72
     vielä
    -0.70
     endnu
    -0.68
    Still
    -0.67
    POSITIVE LOGITS
    そういった
    0.55
     acolo
    0.54
     Exacts
    0.54
     Exactos
    0.53
     كومونز
    0.50
    Autoritní
    0.49
     gynhyrchwyd
    0.49
     greateſt
    0.48
    Hentet
    0.47
     ویکی‌آمباردا
    0.47
    Activations Density 0.279%

    No Known Activations