© 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. 28-GEMMASCOPE-RES-16K
    11. 8021
    Prev
    Next
    INDEX
    Explanations

    terms related to grass, its types, and their ecological significance

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

    following "grass"

    np_acts-logits-general · gemini-2.0-flash

    grass clippings, roots, or median

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.36
    mahl
    -0.33
     initComponents
    -0.31
     INTERESAR
    -0.31
     discoveries
    -0.30
    centerTitle
    -0.30
     Vienne
    -0.29
     Huber
    -0.28
    ungsver
    -0.28
     discovers
    -0.28
    POSITIVE LOGITS
     Grass
    1.10
     grass
    1.07
    Grass
    1.05
    grass
    1.02
     GRASS
    1.00
     lawn
    0.96
     lawns
    0.95
    GRASS
    0.95
     Lawn
    0.93
     grassland
    0.91
    Activations Density 0.117%

    No Known Activations