© 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. 20-GEMMASCOPE-RES-16K
    11. 3620
    Prev
    Next
    INDEX
    Explanations

    technical explanations of electronic components and their functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Numeric values/measurements after frequency units

    np_acts-logits-general · gemini-2.0-flash

    frequency measurements kHz Hz

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexType
    -0.57
    ustre
    -0.52
    alinga
    -0.51
    Personensuche
    -0.51
    ANTY
    -0.51
    umptive
    -0.51
    ########.
    -0.51
    rostis
    -0.49
    Cyfarwyddwr
    -0.48
    Referencer
    -0.47
    POSITIVE LOGITS
     frequency
    1.50
     frequencies
    1.37
     Frequency
    1.32
    frequency
    1.30
    Frequency
    1.29
     fréquence
    1.29
     freq
    1.27
    freq
    1.25
     frequenza
    1.25
     Frequencies
    1.23
    Activations Density 0.368%

    No Known Activations