© 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. 21-GEMMASCOPE-RES-16K
    11. 16228
    Prev
    Next
    INDEX
    Explanations

    references to processes that involve moving to subsequent stages or items

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.62
    цездатний
    -0.58
     initWithFrame
    -0.54
    CodeAnalysis
    -0.50
    featureID
    -0.49
     esternos
    -0.49
     defStyle
    -0.49
    XmlEnum
    -0.47
     Abp
    -0.47
    vode
    -0.46
    POSITIVE LOGITS
     next
    4.58
    next
    3.99
    Next
    3.58
     Next
    3.43
     NEXT
    3.14
    NEXT
    2.98
     nächste
    2.89
     nästa
    2.84
     nächsten
    2.80
     prochaine
    2.78
    Activations Density 0.696%

    No Known Activations