© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 5540
    Prev
    Next
    INDEX
    Explanations

    references to personal liability and accountability in legal contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    legal terminology and phrases related to liability, personal responsibility, and financial/legal documentation.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     democrática
    -0.34
    (||
    -0.33
     géant
    -0.33
     orígenes
    -0.33
     verg
    -0.33
     deberes
    -0.33
     voisins
    -0.33
     pihaknya
    -0.33
    riffe
    -0.32
    neighbours
    -0.32
    POSITIVE LOGITS
     يتيمه
    0.84
    Personendaten
    0.83
     personally
    0.80
     individual
    0.79
    individual
    0.78
     الحره
    0.77
    Individual
    0.76
     individually
    0.75
     personal
    0.73
     INDIVIDUAL
    0.73
    Activations Density 0.461%

    No Known Activations