© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1979
    Prev
    Next
    INDEX
    Explanations

    concepts related to radio frequency and transmission technology

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

    Signals related to radio broadcasting

    np_acts-logits-general · gemini-2.0-flash

    radio stations and wireless signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     film
    -0.33
     movie
    -0.32
     work
    -0.31
     
    -0.31
    ↵↵
    -0.30
     Gu
    -0.29
    •
    -0.28
     gu
    -0.28
      
    -0.28
    Film
    -0.27
    POSITIVE LOGITS
     rádio
    1.16
     radio
    1.11
     radios
    1.05
     RADIO
    1.02
    Radio
    0.98
     Radios
    0.98
     Radio
    0.96
    radio
    0.96
    無線
    0.93
    featureID
    0.92
    Activations Density 0.495%

    No Known Activations