© 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. 6-GEMMASCOPE-RES-16K
    11. 4122
    Prev
    Next
    INDEX
    Explanations

    Java programming language references, particularly relating to its libraries and annotations

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/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.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    EASY
    -0.52
    rouille
    -0.51
    وص
    -0.51
     hati
    -0.51
    Revenir
    -0.50
    心的
    -0.48
    Edm
    -0.48
     اليمن
    -0.48
    مئ
    -0.47
     Virtue
    -0.47
    POSITIVE LOGITS
    +#+
    0.88
     שוליים
    0.86
    новниш
    0.83
    principalColumn
    0.81
    PreferredItem
    0.81
     мәкал
    0.80
    HtmlAttribute
    0.79
    ViewFeatures
    0.79
    posedge
    0.76
     BoxDecoration
    0.75
    Activations Density 0.015%

    No Known Activations