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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 11945
    Prev
    Next
    INDEX
    Explanations

    terms related to boundaries, limits, and definitions within various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by prepositions

    np_acts-logits-general · gemini-2.0-flash

    limits or boundaries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Background
    -0.49
     boire
    -0.49
    myspace
    -0.48
    IVIA
    -0.48
    BACKGROUND
    -0.45
     plomo
    -0.45
     ausser
    -0.45
     बे
    -0.44
     outright
    -0.43
    RESUMEN
    -0.43
    POSITIVE LOGITS
    SerializedSize
    0.96
    NameInMap
    0.94
    IndentedString
    0.90
    Tikang
    0.88
     Савезне
    0.81
    IntoConstraints
    0.79
     NSCoder
    0.79
    richTextPanel
    0.78
    TextHelper
    0.78
     AssemblyCulture
    0.77
    Activations Density 0.436%

    No Known Activations