© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 19-GEMMASCOPE-RES-16K
    11. 8140
    Prev
    Next
    INDEX
    Explanations

    terms related to comparisons and evaluations between different methodologies or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ddots
    -0.59
    ❉
    -0.55
    räge
    -0.52
     remar
    -0.49
    TestingModule
    -0.49
    SerializedSize
    -0.48
    hisattva
    -0.48
    WritableDatabase
    -0.47
     mineures
    -0.47
     unpublished
    -0.47
    POSITIVE LOGITS
     traditional
    2.15
     conventional
    2.04
    traditional
    1.88
    Traditional
    1.83
     Traditional
    1.76
     Conventional
    1.70
    conventional
    1.69
    Conventional
    1.68
     tradicional
    1.56
     traditionnelle
    1.56
    Activations Density 1.511%

    No Known Activations