© 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. 13-GEMMASCOPE-RES-16K
    11. 2287
    Prev
    Next
    INDEX
    Explanations

    specific scientific notation and references within a document

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ########.
    -0.80
    Controllo
    -0.74
     autorytatywna
    -0.71
     protoimpl
    -0.69
    $_['
    -0.66
    хьтан
    -0.66
     CreateTagHelper
    -0.65
    Collegamenti
    -0.63
    RTEX
    -0.62
    afficheront
    -0.61
    POSITIVE LOGITS
    Rhestr
    0.90
     kasarigan
    0.86
    UnusedPrivate
    0.75
    </i>
    0.70
    </em>
    0.62
    DebuggerNonUser
    0.54
    ծ
    0.53
    InitStruct
    0.53
    Sklici
    0.52
    Véxase
    0.50
    Activations Density 0.455%

    No Known Activations