© 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. 5-GEMMASCOPE-RES-16K
    11. 5839
    Prev
    Next
    INDEX
    Explanations

    references to time-related events and sequences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    add
    -0.46
    by
    -0.43
    FileChooser
    -0.41
    OK
    -0.40
    ידי
    -0.38
    adple
    -0.37
    LookUp
    -0.37
    udessa
    -0.37
    map
    -0.37
     envie
    -0.35
    POSITIVE LOGITS
    ########.
    0.91
    Personensuche
    0.88
     AssemblyCulture
    0.84
     defStyle
    0.83
     propOrder
    0.82
    AddTagHelper
    0.79
     springfox
    0.78
    ViewFeatures
    0.78
    Portail
    0.75
    بوابة
    0.75
    Activations Density 0.201%

    No Known Activations