© 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. 5250
    Prev
    Next
    INDEX
    Explanations

    citations and references related to academic or historical discussions

    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
     оригіналу
    -0.46
     nahilalakip
    -0.41
     pungkasnya
    -0.39
    Referanser
    -0.38
    зраст
    -0.36
     hoek
    -0.35
    Theoretical
    -0.32
     Theoretical
    -0.31
     teo
    -0.31
     吋
    -0.31
    POSITIVE LOGITS
     historians
    1.41
     historian
    1.32
     Historian
    1.18
     historiador
    1.17
     histor
    1.16
     Hist
    1.13
    Hist
    1.09
     Histor
    1.02
    hist
    1.02
     HIST
    1.00
    Activations Density 0.257%

    No Known Activations