© 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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 5614
    Prev
    Next
    INDEX
    Explanations

    specific geometric shapes and their properties in mathematical contexts

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

    Geometric shapes (triangles, squares, rectangles)

    np_acts-logits-general · gemini-2.0-flash

    triangle, square, rectangle, polygon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.78
    Personendaten
    -0.77
    __(/*!
    -0.75
    GIVEREF
    -0.67
    AddTagHelper
    -0.66
     CURLOPT
    -0.66
    ]")]
    -0.64
     Seeder
    -0.63
    </thead>
    -0.62
    róleo
    -0.59
    POSITIVE LOGITS
     triangle
    1.35
     rectangle
    1.30
     triangles
    1.25
     square
    1.18
     rectangles
    1.18
     Rectangle
    1.13
     squares
    1.13
     Triangle
    1.11
    triangle
    1.11
     rectangular
    1.11
    Activations Density 0.580%

    No Known Activations