© 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. 4987
    Prev
    Next
    INDEX
    Explanations

    historical references to political entities and governance structures

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

    temporal succession

    np_acts-logits-general · gemini-2.0-flash

    historical and temporal sequences

    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
     للاسماء
    -0.64
    writeFieldEnd
    -0.50
    enumii
    -0.50
     resourceCulture
    -0.49
     withal
    -0.45
     avviene
    -0.45
    KURZBESCHREIBUNG
    -0.44
     Италијани
    -0.43
    :✨
    -0.42
    rungsseite
    -0.42
    POSITIVE LOGITS
     eventually
    1.03
     later
    0.97
     puis
    0.95
     сначала
    0.94
     initially
    0.93
     Eventually
    0.88
    Eventually
    0.88
    eventually
    0.87
     subsequently
    0.85
     successively
    0.84
    Activations Density 0.635%

    No Known Activations