© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 14933
    Prev
    Next
    INDEX
    Explanations

    terms related to data handling and network communication

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

    after "target" or "destination"

    np_acts-logits-general · gemini-2.0-flash

    target destination

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.64
    AccessorTable
    -0.60
     дописавши
    -0.57
    setVerticalGroup
    -0.56
    ineno
    -0.55
     '\\;'
    -0.54
     للمعارف
    -0.53
    ValueStyle
    -0.49
     Ause
    -0.49
    zzleHttp
    -0.47
    POSITIVE LOGITS
     target
    1.89
     destination
    1.85
    target
    1.70
    Target
    1.57
     Target
    1.57
    destination
    1.54
     destino
    1.52
     Destination
    1.43
     cible
    1.41
    Destination
    1.40
    Activations Density 0.739%

    No Known Activations