© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 15890
    Prev
    Next
    INDEX
    Explanations

    instances of the word "loop" and related variations, indicating a focus on iterative processes or structures in programming or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.92
     تانيه
    -0.74
     Sted
    -0.71
     assolu
    -0.70
     gloire
    -0.70
     للمعارف
    -0.69
    SAE
    -0.69
     marten
    -0.69
     compleanno
    -0.69
    +#+
    -0.68
    POSITIVE LOGITS
     loop
    1.64
    loop
    1.52
     Loop
    1.50
     loops
    1.49
     LOOP
    1.43
    Loop
    1.42
    LOOP
    1.37
     Loops
    1.37
    loops
    1.22
     circle
    1.16
    Activations Density 0.187%

    No Known Activations