© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 12034
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating connections, comparisons, or contrasts in arguments

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Follows conjunctions like "and" or "or"

    np_acts-logits-general · gemini-2.0-flash

    obligation and existence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Италијани
    -0.70
    ImageContext
    -0.68
     CURIAM
    -0.68
     disambiguazione
    -0.66
    :✨
    -0.66
     Normdatei
    -0.63
    Rüyada
    -0.60
    цездатний
    -0.59
    énario
    -0.59
     OMITBAD
    -0.59
    POSITIVE LOGITS
     will
    0.50
     should
    0.48
     continues
    0.46
     ought
    0.42
    should
    0.41
     shall
    0.38
     đang
    0.38
     continue
    0.38
    continue
    0.37
     seguirá
    0.35
    Activations Density 0.305%

    No Known Activations