© 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. 30-GEMMASCOPE-RES-16K
    11. 10723
    Prev
    Next
    INDEX
    Explanations

    expressions related to incidents and legal actions

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

    specific months

    np_acts-logits-general · gemini-2.0-flash

    temporal indicators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    الحياه
    -0.52
    webElementGuid
    -0.50
    -------------</
    -0.50
    Personendaten
    -0.50
    fromnode
    -0.48
     ProtoMessage
    -0.47
     snippetHide
    -0.47
    alakip
    -0.47
    bkz
    -0.47
     &___
    -0.46
    POSITIVE LOGITS
     naquele
    1.34
    那天
    1.30
    当天
    1.25
    當天
    1.25
    この日は
    1.13
    同年
    1.07
    この日
    1.06
     daquele
    1.05
     aquel
    0.98
    翌
    0.96
    Activations Density 0.936%

    No Known Activations