© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 14591
    Prev
    Next
    INDEX
    Explanations

    words or sequences that include underscores or hyphens

    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
     pleaſure
    -0.74
     itſelf
    -0.73
     purpoſe
    -0.72
     againſt
    -0.72
    ſelf
    -0.70
    ſelves
    -0.69
     ſche
    -0.69
     anſ
    -0.68
     auffi
    -0.66
     Anſ
    -0.66
    POSITIVE LOGITS
    LabelTagHelper
    0.69
     дописавши
    0.65
    RenderAtEndOf
    0.64
    uxxxx
    0.58
     ligiloj
    0.57
     >=",
    0.55
     AssemblyCulture
    0.53
     actionMode
    0.53
    unnitel
    0.51
    IZONTAL
    0.49
    Activations Density 0.252%

    No Known Activations