© 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. 2-GEMMASCOPE-RES-16K
    11. 4589
    Prev
    Next
    INDEX
    Explanations

    instances of the word "returns" and related terms indicating the act of returning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.47
     cauza
    -0.44
     BoxFit
    -0.42
     heapq
    -0.40
     abstrato
    -0.40
     testCase
    -0.39
     {?>
    -0.38
    IsContent
    -0.38
    しくて
    -0.37
     anggaran
    -0.37
    POSITIVE LOGITS
     returning
    1.58
     returns
    1.54
     Returning
    1.46
    Returning
    1.38
    returns
    1.37
    returning
    1.27
     returned
    1.27
     Returns
    1.23
     RETURNS
    1.15
    Returns
    1.13
    Activations Density 0.107%

    No Known Activations