© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 2184
    Prev
    Next
    INDEX
    Explanations

    references to law enforcement actions and the use of force

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.62
     resourceCulture
    -0.62
    SequentialGroup
    -0.61
    Kjelder
    -0.60
     aDecoder
    -0.58
    RenderAtEndOf
    -0.58
    ➌
    -0.56
    XmlType
    -0.55
     purpure
    -0.51
    ChildScrollView
    -0.50
    POSITIVE LOGITS
     tear
    0.83
     riot
    0.80
     gas
    0.80
    Tear
    0.75
    gas
    0.72
     Tear
    0.71
    tear
    0.69
    riot
    0.68
    Riot
    0.68
     Riot
    0.65
    Activations Density 0.166%

    No Known Activations