© 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. 4-GEMMASCOPE-RES-16K
    6. 3952
    Prev
    Next
    INDEX
    Explanations

    phrases that describe common or typical patterns or behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trouvera
    -0.62
    al
    -0.60
     Maher
    -0.60
    램
    -0.59
    ner
    -0.55
    arXiv
    -0.54
     Chiapas
    -0.54
     socks
    -0.53
     Sock
    -0.53
     BUILD
    -0.53
    POSITIVE LOGITS
     usually
    2.19
     normally
    2.16
    normally
    2.07
     typically
    2.04
     Usually
    2.02
    Typically
    2.01
    Usually
    2.00
     Typically
    1.99
    usually
    1.97
    typically
    1.94
    Activations Density 0.101%

    No Known Activations