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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3606
    Prev
    Next
    INDEX
    Explanations

    recommendations and evaluations of books or articles

    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
    цездатний
    -0.64
    XDECREF
    -0.60
    awtextra
    -0.57
    PRWEB
    -0.54
    WSGI
    -0.53
    حياتها
    -0.52
    ाहरण
    -0.51
    ArrowToggle
    -0.51
    حياته
    -0.51
    ɵɵ
    -0.51
    POSITIVE LOGITS
     read
    2.69
     reading
    2.66
    read
    2.19
     reads
    2.11
    reading
    2.10
     Read
    2.01
     Reading
    1.98
    Reading
    1.93
     READ
    1.89
     READING
    1.89
    Activations Density 0.397%

    No Known Activations