© 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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 2933
    Prev
    Next
    INDEX
    Explanations

    numerical data interspersed with social commentary or questions regarding human mortality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ChildScrollView
    -0.67
     autorytatywna
    -0.63
     endforeach
    -0.62
    printStackTrace
    -0.60
    InvalidProtocol
    -0.60
    aarrggbb
    -0.60
     <",
    -0.58
    onalds
    -0.57
    ScopeManager
    -0.57
    ^(@)
    -0.57
    POSITIVE LOGITS
     charbon
    0.59
     simplest
    0.59
     semplici
    0.58
     simple
    0.57
    simple
    0.56
     simply
    0.54
     carbón
    0.54
     semplice
    0.54
     tắt
    0.54
     simplu
    0.53
    Activations Density 0.353%

    No Known Activations