© 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. 18-GEMMASCOPE-RES-16K
    11. 1313
    Prev
    Next
    INDEX
    Explanations

    temporal references related to events and dates

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

    Years

    np_acts-logits-general · gemini-2.0-flash

    founded in

    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
    Chham
    -0.57
     final
    -0.48
    يلات
    -0.48
    ordnung
    -0.47
    ilen
    -0.47
    led
    -0.46
    Recently
    -0.45
     closing
    -0.44
     (
    -0.42
     O
    -0.42
    POSITIVE LOGITS
     begonnen
    1.03
     mulai
    0.96
     inception
    0.94
     angefangen
    0.92
     iniziato
    0.91
     empezaron
    0.91
     dimulai
    0.90
     börja
    0.89
     zacz
    0.88
    เริ่ม
    0.88
    Activations Density 0.186%

    No Known Activations