© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 9803
    Prev
    Next
    INDEX
    Explanations

    elements related to transformation and character abilities in a fictional context

    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
     ProtoMessage
    -0.66
    
    -0.63
    Демографія
    -0.62
    aarrggbb
    -0.60
    :✨
    -0.60
     autorytatywna
    -0.60
    sizeCache
    -0.56
    subpackage
    -0.54
    最快更新
    -0.53
     snippetHide
    -0.52
    POSITIVE LOGITS
     fix
    0.34
     []),
    0.31
     _(
    0.28
     }}$.
    0.28
    Fax
    0.27
     Kent
    0.26
     flag
    0.26
     jegy
    0.26
     Esp
    0.25
     Wikiseite
    0.25
    Activations Density 0.515%

    No Known Activations