© 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. 22-GEMMASCOPE-RES-16K
    11. 15066
    Prev
    Next
    INDEX
    Explanations

    terms related to radio and its various applications and effects

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

    following "radio."

    np_acts-logits-general · gemini-2.0-flash

    radio frequency and resistance

    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
     CreateTagHelper
    -0.68
     Italijani
    -0.65
    rolment
    -0.61
    utilisons
    -0.60
    yntaxException
    -0.60
     transférez
    -0.57
     constaté
    -0.57
     INSEE
    -0.56
    irability
    -0.55
     Профиль
    -0.55
    POSITIVE LOGITS
     waves
    0.72
    waves
    0.66
     stations
    0.64
     silence
    0.60
    actively
    0.58
     station
    0.56
     frequency
    0.56
     wave
    0.56
    frequency
    0.55
    Shack
    0.54
    Activations Density 0.107%

    No Known Activations