© 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-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1564
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate rarity or uniqueness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.46
     Roskov
    -0.45
    fromnode
    -0.42
     Italijanski
    -0.42
    adpleegd
    -0.41
    лтемелер
    -0.40
     otomatig
    -0.40
    InstrumentedTest
    -0.40
    Ծանոթ
    -0.40
    älde
    -0.39
    POSITIVE LOGITS
     among
    0.54
     Bestandteil
    0.52
    disposing
    0.50
     onderdeel
    0.50
     part
    0.48
    的一部分
    0.47
     onOptions
    0.46
    Parmi
    0.46
     parmi
    0.46
     czeka
    0.46
    Activations Density 0.240%

    No Known Activations