© 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. 30-GEMMASCOPE-RES-16K
    11. 10515
    Prev
    Next
    INDEX
    Explanations

    terms related to data transmission and receipt

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

    Tokens after "receive" or "received"

    np_acts-logits-general · gemini-2.0-flash

    receive packet or receipt

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    /*
    -0.54
    featureID
    -0.54
     purpoſe
    -0.50
     surla
    -0.49
     termica
    -0.46
     ArrayAdapter
    -0.45
    BarStyle
    -0.45
     متعلقه
    -0.45
    sizeCache
    -0.43
     AsyncTask
    -0.42
    POSITIVE LOGITS
     Receiving
    0.80
     receive
    0.78
     Receive
    0.78
    Receiving
    0.76
     receiving
    0.74
    RECEIVE
    0.73
    Receive
    0.73
    receive
    0.73
     RECEIVE
    0.69
     receives
    0.67
    Activations Density 0.187%

    No Known Activations