© 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. 15509
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific accuracy and validity in research

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

    before "of"

    np_acts-logits-general · gemini-2.0-flash

    concepts and definitions

    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
     विश्वसनीयता
    -0.60
     وتسجيلات
    -0.56
    uxxxx
    -0.55
     فريبيس
    -0.53
    GEBURTSDATUM
    -0.52
     mechanical
    -0.51
    tonode
    -0.50
     gyhoeddwyd
    -0.50
     AppCompatTheme
    -0.49
    ThroughAttribute
    -0.49
    POSITIVE LOGITS
     MessageBoxIcon
    0.36
     tils
    0.36
    SpringBootTest
    0.36
    aronder
    0.36
     acompañar
    0.35
    unggulan
    0.34
    newcommand
    0.34
    Données
    0.33
     linking
    0.33
    guide
    0.33
    Activations Density 1.058%

    No Known Activations