© 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. 11516
    Prev
    Next
    INDEX
    Explanations

    terms related to railroads and financial metrics

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

    "Railroad" or "percent"

    np_acts-logits-general · gemini-2.0-flash

    Railroad and percent data

    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
     Paglinawan
    -1.10
     nahilalakip
    -1.09
     GenerationType
    -0.97
    OGND
    -0.95
    SizeF
    -0.95
    ../../
    -0.93
    tonsoft
    -0.85
    @@@@@@@@
    -0.82
    Datuak
    -0.81
    medriver
    -0.80
    POSITIVE LOGITS
    ی
    0.84
    a
    0.78
    я
    0.77
    Cuz
    0.75
    și
    0.74
     disks
    0.74
    Behaviors
    0.72
     gages
    0.71
    łem
    0.70
     piú
    0.69
    Activations Density 0.894%

    No Known Activations