© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 16293
    Prev
    Next
    INDEX
    Explanations

    patterns or phrases indicating frequency and commonality in behavior or characteristics

    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
     possibly
    -1.18
     potentially
    -1.11
    possibly
    -1.09
    potentially
    -1.03
     möglicherweise
    -1.01
     conceivably
    -0.98
     apparently
    -0.94
    Possibly
    -0.93
     posiblemente
    -0.92
     Possibly
    -0.91
    POSITIVE LOGITS
    情况下
    0.79
     Either
    0.78
    Either
    0.78
     beginnetje
    0.75
     either
    0.74
    abestanden
    0.73
    احب
    0.71
     noDo
    0.70
     speaking
    0.68
    Associated
    0.66
    Activations Density 0.390%

    No Known Activations