© 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. 3673
    Prev
    Next
    INDEX
    Explanations

    repeated patterns or sequences of characters

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

    "0x" followed by hexadecimal characters

    np_acts-logits-general · gemini-2.0-flash

    hexadecimal codes followed by zero

    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
    principalColumn
    -0.80
     <>",
    -0.75
     ddelweddau
    -0.71
     ReactDOM
    -0.68
    DockStyle
    -0.68
    TestingModule
    -0.63
     Efq
    -0.63
     referenties
    -0.62
    twimg
    -0.61
     JpaRepository
    -0.60
    POSITIVE LOGITS
    ience
    0.59
    zani
    0.51
    PropertyType
    0.47
    ENCES
    0.45
    ENCE
    0.45
    läufe
    0.44
    Properties
    0.44
    PROPERTIES
    0.43
    хран
    0.43
    subsubsection
    0.43
    Activations Density 0.124%

    No Known Activations