© 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. 11-GEMMASCOPE-RES-16K
    11. 8545
    Prev
    Next
    INDEX
    Explanations

    actions related to movement and tactical operations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.64
     المعيارى
    -0.63
    casio
    -0.56
    ModelMap
    -0.56
     好文分享
    -0.56
    mbic
    -0.55
     utafitiHapana
    -0.55
     BoxDecoration
    -0.55
    addCriterion
    -0.54
    <unused43>
    -0.53
    POSITIVE LOGITS
    nloa
    0.32
    instancetype
    0.27
    цездатний
    0.27
     kohdetta
    0.27
    SizeF
    0.26
     stealth
    0.26
     tốc
    0.25
    DotNetBar
    0.25
    忍者
    0.25
     insertion
    0.25
    Activations Density 0.510%

    No Known Activations