© 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. 212
    Prev
    Next
    INDEX
    Explanations

    the presence of significant initial markers or structural elements in text

    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
    RegressionTest
    -0.54
    eabouts
    -0.53
     Chwiliwch
    -0.51
     "]";
    -0.51
    CardModule
    -0.50
    assertEqual
    -0.48
    ⏎
    -0.47
    IVEREF
    -0.47
    AnimationsModule
    -0.46
     Them
    -0.46
    POSITIVE LOGITS
     unlike
    1.10
    unlike
    1.06
     thanks
    1.05
     Unlike
    0.96
     grâce
    0.95
     grazie
    0.94
     Users
    0.94
    Unlike
    0.93
     users
    0.88
     THANKS
    0.88
    Activations Density 0.254%

    No Known Activations