© 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. 3-GEMMASCOPE-RES-16K
    6. 254
    Prev
    Next
    INDEX
    Explanations

    phrases and references related to learning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    BoxShadow
    -0.72
    queline
    -0.69
    ActionEvent
    -0.66
    zhe
    -0.61
    RequiresApi
    -0.60
     Hage
    -0.60
    udsman
    -0.59
     Nilsson
    -0.57
    zzleHttp
    -0.56
    höhung
    -0.56
    POSITIVE LOGITS
     learn
    2.91
     learns
    2.80
     LEARN
    2.71
    learn
    2.70
     Learn
    2.66
    Learn
    2.63
     learning
    2.54
    LEARN
    2.52
     learned
    2.47
     Learning
    2.33
    Activations Density 0.030%

    No Known Activations