© 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. 3770
    Prev
    Next
    INDEX
    Explanations

    contrasting conjunctions and transitions in arguments

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

    Sentences starting with a contrastive conjunction

    np_acts-logits-general · gemini-2.0-flash

    contrast conjunctions

    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
    tvguidetime
    -0.82
    them
    -0.64
     THEM
    -0.62
     ourselves
    -0.60
     herself
    -0.60
     Họ
    -0.55
    ########.
    -0.55
    him
    -0.54
     Himself
    -0.54
     himself
    -0.54
    POSITIVE LOGITS
     there
    1.21
     when
    1.14
     since
    1.06
     if
    0.97
     it
    0.94
     according
    0.90
     poiché
    0.90
     we
    0.88
     during
    0.87
    since
    0.86
    Activations Density 0.638%

    No Known Activations