© 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. 3-GEMMASCOPE-RES-16K
    6. 6881
    Prev
    Next
    INDEX
    Explanations

    instances of the word "plant" and related terms within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     հղումներ
    -0.40
    ValueStyle
    -0.40
    MIDDLEWARE
    -0.39
    gien
    -0.39
     ujednoznacz
    -0.38
    tegra
    -0.37
     güven
    -0.37
    odes
    -0.37
    awe
    -0.37
     Nore
    -0.36
    POSITIVE LOGITS
     plant
    3.72
     Plant
    3.44
    Plant
    3.41
    plant
    3.34
     PLANT
    3.13
    PLANT
    2.89
     plants
    2.72
     Plants
    2.55
    Plants
    2.47
    plants
    2.45
    Activations Density 0.082%

    No Known Activations