© 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. 7801
    Prev
    Next
    INDEX
    Explanations

    conditional phrases and the presence of time-related references in the text

    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
     оригіналу
    -0.48
     strtotime
    -0.46
    anyahu
    -0.45
    زل
    -0.44
     سبيل
    -0.44
     насељу
    -0.44
    nsis
    -0.42
     läh
    -0.42
    strtotime
    -0.41
    initComponents
    -0.41
    POSITIVE LOGITS
     finally
    2.18
    finally
    1.96
     enfin
    1.83
     Finally
    1.78
    Finally
    1.69
    reszcie
    1.69
     наконец
    1.64
     finalmente
    1.56
     lastly
    1.54
     FINALLY
    1.51
    Activations Density 0.143%

    No Known Activations