© 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. 28-GEMMASCOPE-RES-16K
    11. 4288
    Prev
    Next
    INDEX
    Explanations

    topics related to medical conditions and their treatment

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

    Days of the week or related time words

    np_acts-logits-general · gemini-2.0-flash

    days of the week or tomorrow

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     betweenstory
    -0.72
     informée
    -0.69
     queſta
    -0.68
    intios
    -0.65
    OGND
    -0.61
    utilisons
    -0.60
     MONTHLY
    -0.60
    Monthly
    -0.59
    цездатний
    -0.59
     seasonally
    -0.58
    POSITIVE LOGITS
     tomorrow
    1.52
     yesterday
    1.46
     overnight
    1.33
     Monday
    1.33
     Thursday
    1.30
     Yesterday
    1.30
     Friday
    1.29
     Wednesday
    1.26
     Saturday
    1.25
    Yesterday
    1.25
    Activations Density 0.766%

    No Known Activations