© 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. 14399
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "reap" and its related phrases, particularly those involving appearances and events

    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
    AndEndTag
    -0.78
     AssemblyCompany
    -0.72
     propOrder
    -0.71
    FunctionFlags
    -0.65
    contentLoaded
    -0.63
    RenderAtEndOf
    -0.60
    BeginContext
    -0.60
     تضيفلها
    -0.58
    Sprintf
    -0.57
     isInitialized
    -0.57
    POSITIVE LOGITS
     appearance
    2.52
     appeared
    2.51
     appearing
    2.47
     appear
    2.44
     APPE
    2.27
     appearances
    2.26
    appear
    2.23
     appears
    2.21
     Appearance
    2.15
     Appear
    2.11
    Activations Density 0.672%

    No Known Activations