© 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. 9-GEMMASCOPE-RES-16K
    11. 10426
    Prev
    Next
    INDEX
    Explanations

    technical terminology and operational concepts related to systems and data management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 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
     nonUne
    -0.36
     Corrosion
    -0.33
     Feste
    -0.31
     gebo
    -0.30
     fórmula
    -0.29
     corrosion
    -0.29
    izioni
    -0.29
    kosi
    -0.29
    pareja
    -0.29
     носи
    -0.29
    POSITIVE LOGITS
     createSlice
    1.24
    dispatch
    0.98
     dispatch
    0.95
     useDispatch
    0.91
    ngrx
    0.90
     createStore
    0.84
    DispatchToProps
    0.82
     useSelector
    0.82
     Dispatch
    0.82
    Dispatch
    0.79
    Activations Density 0.241%

    No Known Activations