© 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. 35-GEMMASCOPE-RES-16K
    11. 12291
    Prev
    Next
    INDEX
    Explanations

    mathematical and computational terminology associated with numerical methods and simulations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NSCoder
    -0.56
     שוליים
    -0.54
     autorytatywna
    -0.54
    msgTypes
    -0.49
     Administrativna
    -0.47
    OGND
    -0.46
    gameserver
    -0.40
    lujah
    -0.39
    المناصب
    -0.35
     muffins
    -0.34
    POSITIVE LOGITS
     dynamics
    0.83
     Dynamics
    0.79
     temporal
    0.78
     evolution
    0.78
     dynamic
    0.77
    dynamics
    0.76
     timeline
    0.76
     Timeline
    0.73
     evolve
    0.73
     Temporal
    0.72
    Activations Density 2.159%

    No Known Activations