© 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. 22-GEMMASCOPE-RES-16K
    11. 6427
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrasting points or conditions

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

    Followed by transitional words

    np_acts-logits-general · gemini-2.0-flash

    contrasting conjunctions or punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sær
    -0.54
    olm
    -0.48
    %=
    -0.47
    pyx
    -0.46
    fiehlt
    -0.45
    はじめに
    -0.43
     initially
    -0.43
     originally
    -0.43
    ukup
    -0.43
     before
    -0.42
    POSITIVE LOGITS
     Conversely
    2.26
    Conversely
    2.22
     conversely
    2.21
     meanwhile
    2.00
     Meanwhile
    1.76
    Meanwhile
    1.74
     contrast
    1.70
     dagegen
    1.67
     hingegen
    1.67
     sebaliknya
    1.50
    Activations Density 0.407%

    No Known Activations