© 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. 15031
    Prev
    Next
    INDEX
    Explanations

    numbers and codes related to legal or regulatory references

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

    Numbers, often with hyphens or in phone numbers

    np_acts-logits-general · gemini-2.0-flash

    phone numbers and codes

    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
    ContentAlignment
    -0.64
    TabIndex
    -0.63
    DotNetBar
    -0.63
    ChildScrollView
    -0.59
    ագրություններ
    -0.56
     getSystem
    -0.56
    ulite
    -0.56
    FFF
    -0.55
     kutu
    -0.53
    LBL
    -0.52
    POSITIVE LOGITS
     Geraadpleegd
    0.53
    []=$
    0.52
     الرياضيه
    0.50
     szóci
    0.50
    กระท
    0.48
     referenties
    0.48
     OFDb
    0.47
     Insee
    0.47
    igneurs
    0.46
     vừa
    0.46
    Activations Density 0.249%

    No Known Activations