© 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. 19-GEMMASCOPE-RES-16K
    11. 6102
    Prev
    Next
    INDEX
    Explanations

    numerical data and conversions

    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
     stran
    -0.43
    gh
    -0.41
    فه
    -0.39
    hus
    -0.38
     st
    -0.37
     tinh
    -0.36
    izarse
    -0.34
    ding
    -0.34
    tal
    -0.33
     plă
    -0.33
    POSITIVE LOGITS
     mergeFrom
    0.92
    RegressionTest
    0.89
    ValueStyle
    0.88
    thâu
    0.86
    HideFlags
    0.85
    InjectAttribute
    0.84
    IsMutable
    0.84
    featureID
    0.82
    onViewCreated
    0.82
     ddelweddau
    0.81
    Activations Density 0.506%

    No Known Activations