© 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. 20-GEMMASCOPE-RES-16K
    11. 10403
    Prev
    Next
    INDEX
    Explanations

    programming terminology related to data types and memory management

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

    64-bit integers (Int64, Long) and related constants

    np_acts-logits-general · gemini-2.0-flash

    Long or int size

    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
    IUrlHelper
    -0.72
     htons
    -0.68
    awtextra
    -0.66
    #+#
    -0.63
    Itoa
    -0.61
    出版年
    -0.60
    migrationBuilder
    -0.59
     shallo
    -0.58
     المعيارى
    -0.58
     BoxFit
    -0.57
    POSITIVE LOGITS
     long
    1.59
    long
    1.51
    Long
    1.34
     Long
    1.33
     LONG
    1.10
    LONG
    1.01
     lång
    0.94
     longs
    0.92
     longo
    0.89
    setLong
    0.88
    Activations Density 0.543%

    No Known Activations