© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9097
    Prev
    Next
    INDEX
    Explanations

    references to trained professionals or the concept of training itself

    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
    相
    -0.57
    ه
    -0.56
     platform
    -0.50
    рин
    -0.50
    .
    -0.50
    Destination
    -0.49
     péri
    -0.49
    e
    -0.47
    y
    -0.47
     Ed
    -0.47
    POSITIVE LOGITS
     trained
    2.04
     Trained
    1.98
    Trained
    1.95
    trained
    1.89
     taught
    1.67
    taught
    1.52
     Taught
    1.51
     educated
    1.32
     untrained
    1.28
    educated
    1.25
    Activations Density 0.129%

    No Known Activations