© 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. 11-GEMMASCOPE-RES-16K
    11. 9329
    Prev
    Next
    INDEX
    Explanations

    patterns and discussions around retrospective studies and their impacts in various fields

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    expandindo
    -0.66
    wną
    -0.60
     />';
    -0.57
     />";
    -0.56
     $_"
    -0.55
    sief
    -0.54
    othelioma
    -0.54
     {};
    -0.53
    Gambas
    -0.53
    phyllum
    -0.53
    POSITIVE LOGITS
     '\\;'
    0.63
    FormTagHelper
    0.51
     existed
    0.51
    dafx
    0.50
    原来
    0.48
    isfile
    0.47
     hitherto
    0.47
     esist
    0.46
     exist
    0.46
     missed
    0.46
    Activations Density 0.503%

    No Known Activations