© 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. 6843
    Prev
    Next
    INDEX
    Explanations

    words indicating dependency or condition in complex sentence structures

    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
     noDo
    -0.58
    featureID
    -0.56
    queryInterface
    -0.55
    ContentAsync
    -0.52
    MessageTagHelper
    -0.52
    AnimationsModule
    -0.52
     ſever
    -0.52
    ſelf
    -0.50
     ſol
    -0.50
     ſtate
    -0.50
    POSITIVE LOGITS
     который
    1.28
     který
    1.26
     которые
    1.24
     které
    1.21
     ktorý
    1.19
     które
    1.16
     která
    1.16
     który
    1.16
     ktoré
    1.16
     которая
    1.15
    Activations Density 0.078%

    No Known Activations