© 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. 21-GEMMASCOPE-RES-16K
    11. 7664
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditions or contexts that allow individuals to act freely

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     niedersachsen
    -0.66
     iſt
    -0.63
     myſelf
    -0.62
    
    -0.60
     auffi
    -0.57
     Efq
    -0.55
    enumii
    -0.55
     {?>
    -0.54
     whoſe
    -0.54
     Jefus
    -0.53
    POSITIVE LOGITS
     please
    1.28
     pleases
    1.18
     Please
    1.03
    please
    1.02
     wish
    1.01
     pleased
    0.99
    Please
    0.89
     wishes
    0.87
     PLEASE
    0.82
     wished
    0.82
    Activations Density 0.149%

    No Known Activations