© 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. 5-GEMMASCOPE-RES-16K
    11. 5569
    Prev
    Next
    INDEX
    Explanations

    references to public disturbances or controversies

    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
    arlı
    -0.47
     Gump
    -0.47
     Speise
    -0.47
     Frühstück
    -0.47
    AnchorTagHelper
    -0.47
    lioma
    -0.46
    Weaknesses
    -0.46
    ؤية
    -0.45
     élo
    -0.45
    paj
    -0.43
    POSITIVE LOGITS
     uproar
    1.36
     commotion
    1.33
     fuss
    1.23
     controversy
    1.18
     fanfare
    1.07
     Controversy
    1.05
     hype
    1.02
    fuss
    1.01
     ruck
    0.97
     furo
    0.96
    Activations Density 0.262%

    No Known Activations