© 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. 19-GEMMASCOPE-RES-16K
    11. 12061
    Prev
    Next
    INDEX
    Explanations

    mentions of violent incidents or casualties related to protests or military actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/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.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    styleType
    -0.48
     JUGA
    -0.47
     Eich
    -0.47
     isle
    -0.47
     ditu
    -0.47
     Llu
    -0.46
     Mika
    -0.45
     Brasil
    -0.45
     Sinks
    -0.44
    URIComponent
    -0.44
    POSITIVE LOGITS
     Afghanistan
    1.48
     Afghan
    1.45
     Kabul
    1.39
    Afghanistan
    1.35
     Taliban
    1.35
    Afghan
    1.28
     afghan
    1.24
     Afghans
    1.18
     Afgan
    1.13
    ABUL
    1.10
    Activations Density 0.116%

    No Known Activations