© 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. 20-GEMMASCOPE-RES-16K
    11. 9509
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

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

    LaTeX mathematical expressions and notation, particularly brackets and delimiters like \left, \right, and \langle.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
     ujednoznacz
    -0.82
     kaarangay
    -0.75
    msgTypes
    -0.74
     bezeichneter
    -0.73
    دانشنامهٔ
    -0.70
     queſta
    -0.68
    parsedMessage
    -0.64
    XmlEnum
    -0.62
    ByVersion
    -0.62
    IsMutable
    -0.62
    POSITIVE LOGITS
    left
    1.27
    <b>
    0.78
    <strong>
    0.73
    <em>
    0.73
    <i>
    0.72
     left
    0.63
    Left
    0.63
    LEFT
    0.62
    <u>
    0.60
     betrekking
    0.57
    Activations Density 0.072%

    No Known Activations