© 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-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 162
    Prev
    Next
    INDEX
    Explanations

    references to Unix epoch time and related datetime concepts

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

    Unix timestamps

    np_acts-logits-general · gemini-2.0-flash

    timestamps and numbers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     igjen
    -0.35
     szí
    -0.35
     кӀош
    -0.35
     month
    -0.35
     prefeitura
    -0.34
     schwach
    -0.34
    颜
    -0.34
     læng
    -0.34
    aksikan
    -0.33
    dă
    -0.32
    POSITIVE LOGITS
     snippetHide
    0.70
    twimg
    0.66
    abestanden
    0.59
    AnchorStyles
    0.52
    ConverterFactory
    0.51
    openzeppelin
    0.51
    MemoryWarning
    0.50
    GraphicsUnit
    0.50
     CALIFORNIA
    0.50
    FunctionFlags
    0.49
    Activations Density 0.260%

    No Known Activations