© 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. 24-GEMMASCOPE-RES-16K
    11. 4032
    Prev
    Next
    INDEX
    Explanations

    references to incidents or testimonies involving crime and evidence

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

    apartments and automobiles

    np_acts-logits-general · gemini-2.0-flash

    apartment, automobile, groceries, beer, wallpapers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    errHandler
    -0.81
     microbiome
    -0.71
     sustainably
    -0.70
    ustainable
    -0.70
     crowdfunding
    -0.70
     GoFundMe
    -0.69
     Airbnb
    -0.68
     DSLR
    -0.68
     GoPro
    -0.67
    IsPostBack
    -0.67
    POSITIVE LOGITS
     groote
    0.58
     internes
    0.56
     automobile
    0.56
     RADIO
    0.56
     muß
    0.54
    radio
    0.53
     radio
    0.53
     daß
    0.52
     ciga
    0.52
     automó
    0.51
    Activations Density 0.861%

    No Known Activations