© 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. 19-GEMMASCOPE-RES-16K
    11. 15426
    Prev
    Next
    INDEX
    Explanations

    legal statutes and regulations regarding health and criminal procedures

    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
    expandindo
    -0.75
    GraphicsUnit
    -0.68
     архивлан
    -0.68
    onViewCreated
    -0.68
     allAfrica
    -0.65
    JsonFormat
    -0.63
    Slf
    -0.63
    ImageContext
    -0.61
    InjectAttribute
    -0.61
    Lähteet
    -0.61
    POSITIVE LOGITS
     Act
    0.74
     act
    0.67
    Act
    0.63
    act
    0.63
     Bill
    0.50
    Personendaten
    0.50
     싶
    0.47
     bill
    0.47
     ACT
    0.47
    Bill
    0.47
    Activations Density 0.278%

    No Known Activations