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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 2409
    Prev
    Next
    INDEX
    Explanations

    phrases that denote relationships or connections between various subjects or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     two
    -0.77
     TWO
    -0.58
    two
    -0.57
     zweier
    -0.55
     deux
    -0.55
     zwei
    -0.53
     dwóch
    -0.53
     three
    -0.53
    兩個
    -0.50
     dois
    -0.48
    POSITIVE LOGITS
     stessi
    0.51
     stesse
    0.50
     المعيارى
    0.49
     personeel
    0.48
    Younger
    0.47
     finest
    0.47
     younger
    0.47
     newer
    0.46
     spesa
    0.46
    bibitem
    0.45
    Activations Density 0.135%

    No Known Activations