© 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. 15580
    Prev
    Next
    INDEX
    Explanations

    the presence of references to specific authors or researchers, particularly those with the name "Van"

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

    "Van" followed by another word

    np_acts-logits-general · gemini-2.0-flash

    van/Van/von followed by names

    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
    JspWriter
    -0.43
    round
    -0.42
    kháu
    -0.41
    scryfall
    -0.38
     Савезне
    -0.37
    Демографія
    -0.37
    qrst
    -0.36
     NgModule
    -0.36
     חיצוניים
    -0.36
    tre
    -0.35
    POSITIVE LOGITS
     Van
    0.69
    Van
    0.61
     der
    0.57
     VAN
    0.56
    wapV
    0.54
     van
    0.51
     vanil
    0.47
     pinulongan
    0.46
     Vanderbilt
    0.44
    readFileSync
    0.43
    Activations Density 0.079%

    No Known Activations