© 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-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 12644
    Prev
    Next
    INDEX
    Explanations

    discussions related to race, ethnicity, and social justice in educational programming and clinical trials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
     BoxDecoration
    -0.72
    bootstrapcdn
    -0.66
    LLocation
    -0.63
    ConstraintMaker
    -0.57
    ValueGeneration
    -0.57
    tagHelper
    -0.57
    AutoresizingMask
    -0.56
    cdnjs
    -0.55
    SequentialGroup
    -0.55
     فريبيس
    -0.55
    POSITIVE LOGITS
    expandindo
    1.17
     kaarangay
    0.91
    osoba
    0.88
    ंदीखरीदारी
    0.87
     CanadaChoose
    0.86
     nahilalakip
    0.84
     дописавши
    0.84
     cauſe
    0.83
     purpoſe
    0.82
     ſtate
    0.81
    Activations Density 62.601%

    No Known Activations