© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9028
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "Rad" along with its various forms and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EventBus
    -0.36
     Pub
    -0.36
     EU
    -0.36
    AutoField
    -0.36
    oplas
    -0.34
     Imp
    -0.32
    thée
    -0.32
     proce
    -0.31
    =|
    -0.31
     attended
    -0.31
    POSITIVE LOGITS
     Rad
    1.97
    Rad
    1.95
     RAD
    1.77
     rad
    1.74
     radi
    1.58
    rad
    1.55
    RAD
    1.52
     Radi
    1.46
    Radio
    1.44
     radio
    1.43
    Activations Density 1.396%

    No Known Activations