© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 9890
    Prev
    Next
    INDEX
    Explanations

    terms related to radio technology and communication systems

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

    radio or antennas

    np_acts-logits-general · gemini-2.0-flash

    radio and antenna systems

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUpEnabled
    -0.35
    face
    -0.35
     Kammer
    -0.34
     bike
    -0.33
     escor
    -0.33
     Horror
    -0.32
     horror
    -0.32
    MVC
    -0.31
     GetYourGuide
    -0.31
     kasarigan
    -0.31
    POSITIVE LOGITS
     radio
    1.19
     Radio
    1.07
     RADIO
    1.02
    Radio
    1.01
    radio
    1.00
     antenna
    0.99
     rádio
    0.98
    RADIO
    0.96
     antennas
    0.93
     Antenna
    0.92
    Activations Density 0.756%

    No Known Activations