© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 5990
    Prev
    Next
    INDEX
    Explanations

    mentions of demos and examples related to code or application development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    artifactId
    -0.43
    itteet
    -0.41
     and
    -0.40
     up
    -0.39
    ệc
    -0.39
     late
    -0.39
    AndEndTag
    -0.39
     BoxFit
    -0.38
    likle
    -0.38
    +#+
    -0.38
    POSITIVE LOGITS
     demo
    1.14
     Demo
    1.07
     DEMO
    1.02
     Sample
    1.01
     demos
    1.01
     Demos
    1.00
    Demo
    0.98
    demo
    0.97
     Demonstration
    0.96
    Sample
    0.94
    Activations Density 0.407%

    No Known Activations