© 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. 10-GEMMASCOPE-RES-16K
    11. 8773
    Prev
    Next
    INDEX
    Explanations

    phrases and comparisons that highlight differences in treatment or situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteBarrier
    -0.95
    :✨
    -0.89
     صوتيه
    -0.87
    RegressionTest
    -0.85
    Datuak
    -0.84
    CodedInputStream
    -0.79
     متعلقه
    -0.78
    DrawerToggle
    -0.77
     Wiktionnaire
    -0.76
     []).
    -0.76
    POSITIVE LOGITS
    compare
    0.64
     compare
    0.64
    compar
    0.63
     compared
    0.62
     compar
    0.58
    Compare
    0.55
    compared
    0.54
     comparison
    0.54
     compares
    0.54
     Comparison
    0.53
    Activations Density 0.215%

    No Known Activations