© 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. 12-GEMMASCOPE-RES-16K
    11. 14484
    Prev
    Next
    INDEX
    Explanations

    references to laboratory procedures and washing steps in experimental protocols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    laboratory protocol wash/rinse steps using buffers or saline, often with specified repetitions and times.

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.49
     MainAxisSize
    -0.48
     numerus
    -0.43
     članak
    -0.43
    fxml
    -0.39
     ContentValues
    -0.39
     createSlice
    -0.37
    IsContent
    -0.37
    UVWXYZ
    -0.36
    IntoConstraints
    -0.36
    POSITIVE LOGITS
     washes
    1.16
     wash
    1.16
     washed
    1.07
     washing
    1.04
     Wash
    1.03
     rinsing
    1.02
     rinse
    1.00
    Wash
    1.00
     Washing
    0.98
    washed
    0.97
    Activations Density 0.274%

    No Known Activations