© 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. 10-GEMMASCOPE-RES-16K
    11. 14754
    Prev
    Next
    INDEX
    Explanations

    function definitions and component interactions in code

    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
     and
    -0.50
    keySet
    -0.48
    UnusedPrivate
    -0.48
     In
    -0.48
     No
    -0.47
    ,
    -0.47
    featureID
    -0.46
    isContained
    -0.44
     The
    -0.43
     put
    -0.43
    POSITIVE LOGITS
     houſe
    1.11
     cauſe
    0.99
     purpoſe
    0.95
     greateſt
    0.91
     fubject
    0.90
     leaſt
    0.90
     leſs
    0.90
     Houſe
    0.88
     Chriftian
    0.87
     ſche
    0.87
    Activations Density 0.523%

    No Known Activations