© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 6736
    Prev
    Next
    INDEX
    Explanations

    references to lights and their states (on/off) and associated actions

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

    States of being switched on or off

    np_acts-logits-general · gemini-2.0-flash

    on or off

    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
     '\\;'
    -0.64
     Seeder
    -0.60
    AntiForgeryToken
    -0.59
    thâu
    -0.58
     AspNetCore
    -0.57
     CURIAM
    -0.56
    دانشنامهٔ
    -0.54
    copa
    -0.54
    ⓧ
    -0.54
    resave
    -0.51
    POSITIVE LOGITS
     switched
    1.50
     switch
    1.44
     turned
    1.36
     switches
    1.28
    switch
    1.22
     turn
    1.22
     Turned
    1.19
     switching
    1.19
     Switch
    1.17
     Turn
    1.14
    Activations Density 0.380%

    No Known Activations