© 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. 2-GEMMASCOPE-RES-16K
    6. 4625
    Prev
    Next
    INDEX
    Explanations

    references to transmission, particularly in a technical or communication context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Parcelize
    -0.41
    preference
    -0.40
    Jad
    -0.39
    értel
    -0.39
     preference
    -0.38
    balleur
    -0.38
     Approval
    -0.38
    approval
    -0.38
     approval
    -0.37
     Kars
    -0.36
    POSITIVE LOGITS
     transmit
    1.15
     transmission
    1.09
     transmitted
    1.02
     Transmission
    0.98
     transmitting
    0.93
    Transmission
    0.91
     Transmit
    0.90
     transmits
    0.90
     transmitter
    0.87
    transmit
    0.87
    Activations Density 0.131%

    No Known Activations