© 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. 30-GEMMASCOPE-RES-16K
    11. 7427
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "first" and its importance in context

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

    "first" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    first step or instance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     Audiodateien
    -0.44
    licité
    -0.42
    nalpot
    -0.42
     אחרים
    -0.42
     navíc
    -0.40
     länge
    -0.39
    críbete
    -0.38
     alatt
    -0.38
    再次
    -0.38
    ļi
    -0.38
    POSITIVE LOGITS
     two
    0.79
     few
    0.64
     three
    0.59
    principalColumn
    0.59
     piece
    0.54
    SharedDtor
    0.54
    MessageTagHelper
    0.54
     several
    0.54
     batch
    0.54
    WithIOException
    0.53
    Activations Density 0.260%

    No Known Activations