© 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. 2-GEMMASCOPE-RES-16K
    11. 11283
    Prev
    Next
    INDEX
    Explanations

    keywords related to equipment and functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.58
    kheim
    -0.53
     affez
    -0.50
     vettoriale
    -0.49
    httphttps
    -0.49
    InjectAttribute
    -0.48
    glDelete
    -0.47
    pannt
    -0.46
    czema
    -0.46
     compilers
    -0.46
    POSITIVE LOGITS
     equipped
    0.93
     Equipped
    0.74
    equipped
    0.72
    Equipped
    0.69
     accumulation
    0.65
     collection
    0.64
     equipado
    0.64
     lighter
    0.63
     equipping
    0.62
     equip
    0.59
    Activations Density 0.146%

    No Known Activations