© 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. 40-GEMMASCOPE-RES-16K
    11. 5608
    Prev
    Next
    INDEX
    Explanations

    phrases related to grammar and structure in language

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tothe
    -0.79
     vnto
    -0.62
     autorytatywna
    -0.51
    到的
    -0.50
     unto
    -0.48
     thereto
    -0.46
     kasarigan
    -0.46
    到你
    -0.45
     صوتيه
    -0.45
    到了
    -0.44
    POSITIVE LOGITS
     να
    1.33
     să
    1.06
     да
    0.95
     å
    0.78
     zu
    0.77
    ToBe
    0.68
    ที่จะ
    0.66
     jā
    0.66
    să
    0.61
     sicherzustellen
    0.56
    Activations Density 0.207%

    No Known Activations