© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 2173
    Prev
    Next
    INDEX
    Explanations

    key technological advancements in broadcasting

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    "... was ... then" and similar past-tense constructions

    np_acts-logits-general · gemini-2.0-flash

    past events then

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     prochaines
    -0.87
     komende
    -0.68
     Recent
    -0.64
     recent
    -0.64
     prochain
    -0.60
    ]--;
    -0.60
     latest
    -0.60
     kaynağından
    -0.59
     récentes
    -0.59
     prossimo
    -0.58
    POSITIVE LOGITS
     then
    3.14
    then
    2.45
     damals
    2.44
     тогда
    2.38
     entonces
    2.35
    Then
    2.29
     allora
    2.29
     Then
    2.27
     damaligen
    2.20
     THEN
    2.15
    Activations Density 0.576%

    No Known Activations