© 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. 8368
    Prev
    Next
    INDEX
    Explanations

    conjunctive phrases that connect ideas or elements in a narrative

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

    Followed by a coordinating conjunction

    np_acts-logits-general · gemini-2.0-flash

    conjunctions connecting clauses

    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
    ,
    -0.72
     Though
    -0.59
    Though
    -0.59
     though
    -0.57
     Earlier
    -0.56
    Earlier
    -0.55
    contentLoaded
    -0.55
     although
    -0.54
    albeit
    -0.53
    though
    -0.53
    POSITIVE LOGITS
     finally
    0.66
     autorytatywna
    0.65
     then
    0.65
     BoxFit
    0.64
     hurriedly
    0.60
     INTERESAR
    0.60
    헌
    0.58
    }{*}{}
    0.56
    \{\\
    0.56
     asked
    0.56
    Activations Density 0.042%

    No Known Activations