© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16263
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions

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

    LaTeX mathematical notation, particularly expressions involving mathematical symbols and formatting.

    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
     sencillo
    -0.38
     instead
    -0.34
     convertirse
    -0.33
     bēr
    -0.33
     létre
    -0.32
    run
    -0.30
    wendungen
    -0.30
     garantías
    -0.30
     sirvió
    -0.29
    <eos>
    -0.29
    POSITIVE LOGITS
     CreateTagHelper
    0.82
     EconPapers
    0.75
    strut
    0.72
     Monfieur
    0.65
     informée
    0.63
    astify
    0.62
     ſeveral
    0.61
    ंदीखरीदारी
    0.60
    httphttps
    0.60
    mobileqq
    0.60
    Activations Density 0.531%

    No Known Activations