© 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. 9-GEMMASCOPE-RES-16K
    11. 2038
    Prev
    Next
    INDEX
    Explanations

    references to key political figures and events, particularly those related to investigations and controversies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/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.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sivité
    -0.67
    futbolista
    -0.66
    AccessFile
    -0.65
     Norma
    -0.64
     promis
    -0.61
     Edy
    -0.61
    icana
    -0.60
    AppCompatTheme
    -0.60
    nbsp
    -0.59
    ည်
    -0.59
    POSITIVE LOGITS
     bouch
    0.92
     meso
    0.87
    GOTREF
    0.86
    ̣i
    0.85
    imte
    0.82
     kasarigan
    0.80
     newName
    0.78
    λαμβ
    0.77
     Braxton
    0.77
    /−
    0.76
    Activations Density 1.591%

    No Known Activations