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

    Neuronpedia

    Jacobian LensNEW
    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. 10889
    Prev
    Next
    INDEX
    Explanations

    references to historical events and current social issues

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

    current events or time

    np_acts-logits-general · gemini-2.0-flash

    contemporary and modern

    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
    تقاوى
    -0.51
    LabelTagHelper
    -0.50
     autorytatywna
    -0.49
    ("}\
    -0.49
     Italijanski
    -0.45
    PRNewswire
    -0.44
     Infórmanos
    -0.43
     cherchés
    -0.43
     Previously
    -0.41
    BIÉN
    -0.40
    POSITIVE LOGITS
     contemporary
    1.30
     current
    1.26
    contemporary
    1.20
     modern
    1.11
    current
    1.10
     CURRENT
    1.09
    当代
    1.06
    Contemporary
    1.05
    modern
    1.02
     recent
    1.02
    Activations Density 0.479%

    No Known Activations