© 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. 15752
    Prev
    Next
    INDEX
    Explanations

    relative pronouns and clauses suggesting connections or conditions within the text

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

    "that" or "which" followed by a verb

    np_acts-logits-general · gemini-2.0-flash

    clauses that describe nouns

    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
     is
    -0.40
     которые
    -0.39
     are
    -0.39
     which
    -0.38
     kurie
    -0.38
    ugd
    -0.36
     who
    -0.36
    I
    -0.35
    which
    -0.34
     tenemos
    -0.34
    POSITIVE LOGITS
    CppMethod
    0.68
    AnimationsModule
    0.68
    LLocation
    0.68
    出版年
    0.66
    ftagPool
    0.65
    WebServlet
    0.64
    migrationBuilder
    0.64
    Tembelea
    0.60
    AxisAlignment
    0.60
    SerializedSize
    0.59
    Activations Density 0.335%

    No Known Activations