© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3490
    Prev
    Next
    INDEX
    Explanations

    specific technical terms related to radio and communication technology

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

    "radio" and related technology

    np_acts-logits-general · gemini-2.0-flash

    radio technology and applications

    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
    ValueStyle
    -0.57
    RenderAtEndOf
    -0.56
     giudi
    -0.50
     templado
    -0.49
     gius
    -0.48
     <<<<<<<<<<<<<<
    -0.48
    LLVM
    -0.48
     judiciales
    -0.47
    UnitTesting
    -0.47
     poussière
    -0.47
    POSITIVE LOGITS
     radio
    1.38
     Radio
    1.22
     radios
    1.22
     antenna
    1.20
    radio
    1.15
     RADIO
    1.14
     antennas
    1.10
    Radio
    1.10
     VHF
    1.08
     Radios
    1.07
    Activations Density 0.431%

    No Known Activations