© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2723
    Prev
    Next
    INDEX
    Explanations

    descriptions of geometric shapes and their properties

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

    Geometric shapes

    np_acts-logits-general · gemini-2.0-flash

    geometric shapes and forms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NewUrlParser
    -0.61
    viewDidLoad
    -0.60
     propOrder
    -0.53
     समीक्षाओं
    -0.52
    AddTagHelper
    -0.52
     onAnimation
    -0.50
    GIVEREF
    -0.50
     CreateTagHelper
    -0.50
    tonsoft
    -0.48
    loem
    -0.48
    POSITIVE LOGITS
     shape
    1.57
     shapes
    1.42
     Shape
    1.40
     rectangular
    1.35
    shape
    1.32
     shaped
    1.30
    Shape
    1.28
     square
    1.27
     rectangle
    1.25
     SHAPE
    1.24
    Activations Density 0.672%

    No Known Activations