© 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. 33-GEMMASCOPE-RES-16K
    11. 7958
    Prev
    Next
    INDEX
    Explanations

    references to IEEE publications and articles

    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
    +#+
    -0.38
    effetto
    -0.36
     urma
    -0.35
     tă
    -0.33
    Unmanaged
    -0.33
    estinal
    -0.32
     timpul
    -0.32
     liberación
    -0.31
     plă
    -0.31
     Roskov
    -0.31
    POSITIVE LOGITS
     IEEE
    0.75
     насељу
    0.66
    IEEE
    0.65
     propOrder
    0.55
     CreateTagHelper
    0.55
    ieee
    0.52
    chartInstance
    0.52
     ieee
    0.52
     defStyle
    0.49
    PreferredItem
    0.49
    Activations Density 0.395%

    No Known Activations