© 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. 953
    Prev
    Next
    INDEX
    Explanations

    propositions or phrases that express context or conditions in relation to other statements

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

    "With" followed by prepositions or pronouns

    np_acts-logits-general · gemini-2.0-flash

    phrases starting with "with" or "regardless"

    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
    Branch
    -0.29
     only
    -0.28
     Gall
    -0.27
    Y
    -0.27
    上
    -0.27
     the
    -0.26
     branch
    -0.26
     Branch
    -0.26
    y
    -0.25
    branch
    -0.25
    POSITIVE LOGITS
     surla
    1.05
    GEBURTSDATUM
    0.97
    SourceChecksum
    0.94
    Personensuche
    0.83
    WithIOException
    0.82
    Obrázky
    0.78
     nahilalakip
    0.77
     autorytatywna
    0.77
    OGND
    0.77
    NameInMap
    0.77
    Activations Density 0.287%

    No Known Activations