© 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. 5649
    Prev
    Next
    INDEX
    Explanations

    mentions of historical documents and their preservation

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

    preceding locations or institutions

    np_acts-logits-general · gemini-2.0-flash

    collected items and artifacts

    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
    setViewportView
    -0.42
    rsiniz
    -0.36
    pernicus
    -0.36
    loyment
    -0.35
     للمعارف
    -0.35
    jiet
    -0.35
     jobs
    -0.34
     push
    -0.34
    RectangleBorder
    -0.33
     Udemy
    -0.33
    POSITIVE LOGITS
     collezione
    0.65
    DockStyle
    0.65
     coleção
    0.64
     confiscated
    0.63
     colección
    0.62
     museum
    0.61
    museum
    0.60
     collectie
    0.60
    belong
    0.60
     collection
    0.59
    Activations Density 0.256%

    No Known Activations