© 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. 39-GEMMASCOPE-RES-16K
    11. 3594
    Prev
    Next
    INDEX
    Explanations

    concepts related to economic principles and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    非常的
    -0.90
     approximately
    -0.80
    Approximately
    -0.77
     extrêmement
    -0.75
     whatsoever
    -0.74
     absolutamente
    -0.73
    approximately
    -0.72
     beziehungs
    -0.71
     Approximately
    -0.71
    Furthermore
    -0.71
    POSITIVE LOGITS
    何况
    0.59
     чтоб
    0.55
     للمعارف
    0.51
    ={()=>
    0.50
    tfrac
    0.48
    我没
    0.46
     boosted
    0.45
     faves
    0.45
    엔
    0.44
     dodging
    0.44
    Activations Density 2.379%

    No Known Activations