© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6263
    Prev
    Next
    INDEX
    Explanations

    variations of the verb "to be," particularly in the past participle form

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    berdayakan
    -0.68
    HtmlAttribute
    -0.61
    antaranya
    -0.60
     arşivlendi
    -0.57
    ähteet
    -0.56
    ']))
    
    -0.54
     kwiaty
    -0.54
     beschik
    -0.54
    )))
    
    -0.53
     mijne
    -0.52
    POSITIVE LOGITS
    Portail
    0.45
     sein
    0.38
     ir
    0.38
    handleSubmit
    0.37
     kaarangay
    0.37
     IR
    0.36
     الاطلاع
    0.36
    reicher
    0.36
    だった
    0.35
     Ches
    0.35
    Activations Density 0.154%

    No Known Activations