© 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. 16-GEMMASCOPE-RES-16K
    11. 10364
    Prev
    Next
    INDEX
    Explanations

    references to SQL queries and database interactions

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

    SQL queries

    np_acts-logits-general · gemini-2.0-flash

    end of code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     oprot
    -0.67
     notamment
    -0.55
     herself
    -0.53
     themselves
    -0.47
    addCriterion
    -0.47
     consigo
    -0.46
    ادم
    -0.46
    JPL
    -0.45
    ophagus
    -0.44
    pena
    -0.43
    POSITIVE LOGITS
    IntoConstraints
    0.90
    :✨
    0.83
     ExecuteAsync
    0.81
     ***!
    0.76
     متعلقه
    0.74
    下载附件
    0.72
    .*")]
    0.71
    postsleuth
    0.70
    rungsseite
    0.68
    ]")]
    0.67
    Activations Density 0.095%

    No Known Activations