© 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. 3953
    Prev
    Next
    INDEX
    Explanations

    references to identity verification and related legal or bureaucratic processes

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

    Followed by Japanese particles

    np_acts-logits-general · gemini-2.0-flash

    loan or death after release

    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
     
    -0.73
    ,
    -0.71
     (
    -0.69
    .
    -0.66
     is
    -0.65
     B
    -0.64
    -
    -0.64
     to
    -0.63
     that
    -0.63
     "
    -0.62
    POSITIVE LOGITS
     itſelf
    1.10
     myſelf
    1.10
     Reſ
    1.08
     ſche
    1.07
     pleaſure
    1.06
     ―――――
    1.06
     Monfieur
    1.05
     auffi
    1.04
     ſever
    1.02
     Theſe
    1.00
    Activations Density 0.057%

    No Known Activations