© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 5793
    Prev
    Next
    INDEX
    Explanations

    references to XML and JSON data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chtenstein
    -0.86
    ibouti
    -0.67
    Hara
    -0.66
    '])
    -0.66
    cioni
    -0.65
    ENNA
    -0.65
     없습니다
    -0.64
     Varma
    -0.63
    anță
    -0.63
    horizontalLayout
    -0.60
    POSITIVE LOGITS
    ()-
    1.43
    ®-
    1.40
    ′-
    1.39
    *-
    1.30
    }-
    1.26
    '-
    1.26
    &-
    1.24
     %-
    1.23
    -​
    1.23
    )-
    1.22
    Activations Density 1.071%

    No Known Activations