© 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. 3-GEMMASCOPE-RES-16K
    11. 6029
    Prev
    Next
    INDEX
    Explanations

    terms related to reproduction and replicability

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.44
    rijf
    -0.43
    ցված
    -0.41
    WebServlet
    -0.41
    ggars
    -0.40
    tvguidetime
    -0.39
    Personensuche
    -0.39
    -------------</
    -0.39
    astrar
    -0.38
     suaminya
    -0.38
    POSITIVE LOGITS
     reproduce
    1.38
     reproduction
    1.36
     reproducing
    1.29
     reproduces
    1.27
     reproduced
    1.23
     recreation
    1.12
     Reproduction
    1.09
     reprodu
    1.05
    Reproduction
    1.03
     Reprodu
    0.99
    Activations Density 0.109%

    No Known Activations