© 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. 41-GEMMASCOPE-RES-16K
    11. 8121
    Prev
    Next
    INDEX
    Explanations

    Japanese phrases that involve exchanging information or ideas, especially with a notion of reciprocity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     âmes
    -0.76
     Moscú
    -0.69
     oídos
    -0.69
     bankası
    -0.69
     feroit
    -0.69
     rêves
    -0.68
     étoient
    -0.68
     doğum
    -0.67
     étoit
    -0.66
     avoient
    -0.66
    POSITIVE LOGITS
    み
    0.47
    む
    0.47
    じ
    0.46
    め
    0.46
    <?
    0.45
    い
    0.45
    ろ
    0.45
    こ
    0.45
    け
    0.44
    ん
    0.43
    Activations Density 0.010%

    No Known Activations