© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 5326
    Prev
    Next
    INDEX
    Explanations

    references to alarms and patches in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     سكانية
    -0.88
     ControllerBase
    -0.87
    AsUp
    -0.84
    الدراسه
    -0.81
    principalColumn
    -0.80
     Wicidata
    -0.74
    UrlResolution
    -0.71
    脚注の使い方
    -0.70
    almaz
    -0.69
    Referanser
    -0.69
    POSITIVE LOGITS
     alarm
    1.20
     Alarm
    1.03
    patch
    1.00
    alarm
    0.94
     patch
    0.92
    Alarm
    0.90
    Patch
    0.89
     patches
    0.85
     cure
    0.84
     Patch
    0.83
    Activations Density 0.122%

    No Known Activations