© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11526
    Prev
    Next
    INDEX
    Explanations

    connections to specific roles and features in various contexts, particularly regarding social and functional dynamics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    Personensuche
    -0.85
    thâu
    -0.77
     nahilalakip
    -0.75
    ьажоргаш
    -0.74
     EconPapers
    -0.73
     intStringLen
    -0.70
     ब्रेकडाउन
    -0.70
     noDo
    -0.69
    uxxxx
    -0.68
    fjspx
    -0.68
    POSITIVE LOGITS
    ญา
    0.40
    s
    0.38
     
    0.29
    av
    0.28
    ,
    0.27
    l
    0.26
    un
    0.26
     것이다
    0.26
    лік
    0.26
    ori
    0.26
    Activations Density 2.110%

    No Known Activations