© 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. 21-GEMMASCOPE-RES-16K
    11. 2467
    Prev
    Next
    INDEX
    Explanations

    temporal indicators and phrases that denote the timing of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enderror
    -0.60
    TypedDataSet
    -0.59
    NameInMap
    -0.57
     الاطلاع
    -0.57
    IsMutable
    -0.53
    ftagPool
    -0.49
    internalType
    -0.47
     AssemblyTitle
    -0.47
    хьтан
    -0.47
    MemoryWarning
    -0.46
    POSITIVE LOGITS
     thereafter
    1.18
     afterwards
    1.06
     afterward
    1.06
     after
    0.98
     Thereafter
    0.85
     before
    0.84
    after
    0.82
     darauf
    0.76
    SequentialGroup
    0.74
     beforehand
    0.71
    Activations Density 0.123%

    No Known Activations