© 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. 7766
    Prev
    Next
    INDEX
    Explanations

    time intervals and durations expressed in days, weeks, and years

    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
     Theſe
    -0.84
     Efq
    -0.83
     חיצוניים
    -0.71
     Monfieur
    -0.70
     Jefus
    -0.69
     Scotty
    -0.68
     poffible
    -0.67
     getDefault
    -0.66
     fufficient
    -0.66
     himſelf
    -0.66
    POSITIVE LOGITS
    Allgeme
    0.48
    titure
    0.42
     shy
    0.42
     Baillargeon
    0.41
    ELTS
    0.39
     into
    0.39
    setupUi
    0.38
    wezen
    0.37
     år
    0.36
    igneur
    0.36
    Activations Density 0.102%

    No Known Activations