© 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. 16-GEMMASCOPE-RES-16K
    11. 12854
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly related to dates and temporal expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.68
    TagMode
    -0.60
    Personensuche
    -0.53
    oredCriteria
    -0.51
     Италијани
    -0.49
    dorp
    -0.48
     bloat
    -0.48
     Italijanski
    -0.48
     TIA
    -0.47
    stylers
    -0.47
    POSITIVE LOGITS
     Wednesday
    0.76
    Wednesday
    0.70
     Tuesday
    0.70
     Monday
    0.69
     Thursday
    0.68
    Monday
    0.66
    Thursday
    0.65
    Tuesday
    0.60
     Friday
    0.60
    kuuta
    0.59
    Activations Density 0.124%

    No Known Activations