© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6122
    Prev
    Next
    INDEX
    Explanations

    references to scientific offices and their roles in knowledge production and dissemination

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

    ending in "ence" or "Office"

    np_acts-logits-general · gemini-2.0-flash

    reference and office contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    retudo
    -0.57
     pauv
    -0.51
     prière
    -0.51
     Púb
    -0.50
     élector
    -0.47
     chrétien
    -0.47
     pédagog
    -0.47
     douleur
    -0.46
     Jurí
    -0.45
     amitié
    -0.45
    POSITIVE LOGITS
    dence
    0.74
    ence
    0.74
    ANTAGE
    0.73
    ANCE
    0.73
    mage
    0.72
    ance
    0.70
    tice
    0.69
    enge
    0.68
    gence
    0.68
    vantage
    0.68
    Activations Density 0.539%

    No Known Activations