© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 11911
    Prev
    Next
    INDEX
    Explanations

    terms related to giving or acts of generosity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DrawerLayout
    -0.74
     nakalista
    -0.62
    IonicModule
    -0.61
    ThroughAttribute
    -0.58
    SharedCtor
    -0.57
    ftagPool
    -0.57
     חיצוניים
    -0.56
    richTextPanel
    -0.55
    Демографія
    -0.53
    mately
    -0.52
    POSITIVE LOGITS
     rise
    1.09
     birth
    1.08
     credence
    1.01
     away
    0.94
    aways
    0.90
     preference
    0.83
     priority
    0.79
    away
    0.78
    birth
    0.77
     permission
    0.76
    Activations Density 0.204%

    No Known Activations