© 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. 22-GEMMASCOPE-RES-16K
    11. 4583
    Prev
    Next
    INDEX
    Explanations

    technical terms related to signal processing and modulation

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

    Signals with frequency or period

    np_acts-logits-general · gemini-2.0-flash

    frequency, period, amplitude

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Normdatei
    -0.64
     nakalista
    -0.62
     CURIAM
    -0.54
     ziren
    -0.50
     admiten
    -0.43
    iotti
    -0.43
    rolid
    -0.43
    kö
    -0.42
     relegation
    -0.42
     Wikidata
    -0.42
    POSITIVE LOGITS
     frequency
    1.28
     sinusoidal
    1.20
     amplitude
    1.16
     Frequency
    1.12
    frequency
    1.06
     frequencies
    1.06
    Frequency
    1.03
     sinus
    1.02
     Amplitude
    1.01
     FREQUENCY
    1.00
    Activations Density 1.191%

    No Known Activations