© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2135
    Prev
    Next
    INDEX
    Explanations

    phrases related to maintenance and upkeep requirements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "re" or indicating repetition

    np_acts-logits-general · gemini-2.0-flash

    re-consideration or subsequent action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agrí
    -0.59
    rugada
    -0.58
    asteroide
    -0.55
    jsonwebtoken
    -0.52
    Demografía
    -0.52
     <>",
    -0.51
    цездатний
    -0.51
    veloped
    -0.51
    (!__
    -0.51
     <=",
    -0.51
    POSITIVE LOGITS
     re
    1.78
     repeat
    1.77
     Repeat
    1.51
     revisit
    1.49
     rerun
    1.48
     redo
    1.46
    repeat
    1.42
     repeating
    1.39
     повтор
    1.38
     repeats
    1.36
    Activations Density 0.959%

    No Known Activations