© 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. 18-GEMMASCOPE-RES-16K
    11. 9142
    Prev
    Next
    INDEX
    Explanations

    quantities and changes in financial data

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

    "last" or "previous" before time periods

    np_acts-logits-general · gemini-2.0-flash

    last and previous periods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Oggi
    -0.60
     myö
    -0.59
    Skocz
    -0.57
     meille
    -0.54
    äiv
    -0.54
    今でも
    -0.53
    今も
    -0.52
    ıştır
    -0.52
     дописавши
    -0.51
    rivit
    -0.50
    POSITIVE LOGITS
     last
    1.80
     previous
    1.70
    previous
    1.49
    last
    1.47
     förra
    1.41
     Previous
    1.40
    Previous
    1.37
     предыду
    1.36
    Last
    1.31
     Last
    1.25
    Activations Density 0.432%

    No Known Activations