© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 14999
    Prev
    Next
    INDEX
    Explanations

    references to violent protests or confrontations involving demonstrators and police

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ftagPool
    -0.53
    ícola
    -0.52
     Dropout
    -0.49
     referenties
    -0.49
     pesca
    -0.46
     diagnostic
    -0.45
    orcid
    -0.45
     tids
    -0.44
    ronpa
    -0.44
    errHandler
    -0.44
    POSITIVE LOGITS
     riot
    1.27
     riots
    1.12
     protesters
    1.11
     demonstrators
    1.08
     violence
    1.03
     protestors
    1.01
    riot
    0.99
     Riot
    0.98
     mob
    0.97
    Riot
    0.96
    Activations Density 0.292%

    No Known Activations