© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6156
    Prev
    Next
    INDEX
    Explanations

    references to data packet processing and routing in network communications

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

    "destination" or its vicinity

    np_acts-logits-general · gemini-2.0-flash

    destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelper
    -0.60
     Ause
    -0.47
    Искәрмәләр
    -0.45
    windowFixed
    -0.43
    MultipartFile
    -0.41
    <![
    -0.39
    MenuInflater
    -0.39
    lateur
    -0.39
     pride
    -0.37
     lenker
    -0.36
    POSITIVE LOGITS
     destination
    2.39
     destinations
    2.11
    destination
    1.96
     Destination
    1.95
    Destination
    1.89
     destino
    1.84
     Destinations
    1.76
    Destinations
    1.59
     target
    1.58
    目的地
    1.58
    Activations Density 0.372%

    No Known Activations