© 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 EvalsExportsAPI 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. 1494
    Prev
    Next
    INDEX
    Explanations

    references to conditions, choices, and the consequences or impacts of actions

    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
     moje
    -0.93
     mijn
    -0.87
     mojej
    -0.84
     my
    -0.84
     mój
    -0.84
     meu
    -0.82
     minha
    -0.82
     meus
    -0.81
     моих
    -0.80
     мои
    -0.79
    POSITIVE LOGITS
     I
    1.16
     anaknya
    0.63
     we
    0.63
     me
    0.62
    ⤹
    0.54
     informée
    0.54
    Rüyada
    0.53
     я
    0.52
     منم
    0.51
     their
    0.51
    Activations Density 0.672%

    No Known Activations