© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 78313
    Prev
    Next
    INDEX
    Explanations

    references to historical or notable figures, particularly those associated with Caesarean sections or related medical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Caesar, cesarean, caesium

    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
    Not in Any Lists

    No Comments

    Negative Logits
    hí
    -0.33
     înal
    -0.31
     partida
    -0.30
     bailar
    -0.30
     perumahan
    -0.29
    lihood
    -0.29
     tră
    -0.29
    riment
    -0.28
     animado
    -0.28
     lámparas
    -0.28
    POSITIVE LOGITS
     Caesar
    2.05
    Caesar
    1.96
     Caesars
    1.52
     Cæsar
    1.49
     Cesar
    1.28
     César
    1.27
    esar
    1.25
    Cesar
    1.23
     Caes
    1.22
    César
    1.20
    Activations Density 0.008%

    No Known Activations