© 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. 21-GEMMASCOPE-RES-16K
    11. 3731
    Prev
    Next
    INDEX
    Explanations

    superlative phrases that highlight the prominence or excellence of subjects

    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
     Theſe
    -0.56
    ượ
    -0.49
     odpowied
    -0.49
     vœux
    -0.49
     appropriateness
    -0.48
     سرا
    -0.47
     RSSSF
    -0.47
    kolwiek
    -0.47
     situatie
    -0.47
    యా
    -0.46
    POSITIVE LOGITS
     many
    1.28
     few
    1.26
    many
    1.08
    few
    1.04
     MANY
    0.99
     wenigen
    0.96
     vielen
    0.94
     earliest
    0.93
    MANY
    0.93
     rare
    0.90
    Activations Density 0.133%

    No Known Activations