© 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. 1333
    Prev
    Next
    INDEX
    Explanations

    financial terms related to changes in revenue, income, and economic statistics

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

    increases or decreases

    np_acts-logits-general · gemini-2.0-flash

    direction and magnitude of change

    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
     NSCoder
    -0.76
     CreateTagHelper
    -0.75
    ècie
    -0.73
     препратки
    -0.72
    styleType
    -0.69
     ModelExpression
    -0.69
    #
    -0.69
    enumi
    -0.68
     Normdatei
    -0.66
    rrggbb
    -0.66
    POSITIVE LOGITS
     several
    0.72
     
    0.57
     some
    0.55
     approximately
    0.54
     nearly
    0.53
     almost
    0.51
     one
    0.50
     några
    0.50
    のが
    0.50
     cât
    0.49
    Activations Density 0.272%

    No Known Activations