© 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. 3435
    Prev
    Next
    INDEX
    Explanations

    numeric values, particularly related to technology specifications or measurements

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

    "8" followed by a unit of measurement or other context

    np_acts-logits-general · gemini-2.0-flash

    numbers followed by punctuation

    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
     للمعارف
    -0.75
     an
    -0.55
    lwjgl
    -0.53
    enumi
    -0.52
     
    -0.51
    era
    -0.48
     To
    -0.48
    ↵↵
    -0.48
    macht
    -0.48
     des
    -0.47
    POSITIVE LOGITS
     himſelf
    1.08
     myſelf
    1.06
     Jefus
    1.04
     raiſ
    1.01
     Monfieur
    1.00
     themſelves
    0.99
     ſta
    0.97
     ſeveral
    0.96
     Majefty
    0.96
     itſelf
    0.95
    Activations Density 0.702%

    No Known Activations