© 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-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 128801
    Prev
    Next
    INDEX
    Explanations

    biochemical markers and gene expressions related to immune responses and metabolic processes

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

    abbreviations and acronyms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    <bos>
    -0.42
    sunter
    -0.36
    nonatomic
    -0.36
    []){
    -0.35
    reus
    -0.34
     cul
    -0.33
    </i>
    -0.32
     minimum
    -0.32
    cul
    -0.32
    </em>
    -0.32
    POSITIVE LOGITS
    GEBURTSDATUM
    0.67
    脚注の使い方
    0.66
     ویکی‌پدی
    0.60
     validamos
    0.59
    awaiter
    0.59
     tartalomajánló
    0.58
     restauration
    0.57
     alene
    0.57
     Normdatei
    0.56
     Réponses
    0.56
    Activations Density 1.244%

    No Known Activations