Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 662
    Prev
    Next
    INDEX
    Explanations

    occurrences of numerical expressions and mathematical notation

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

    mathematical expressions and variables related to equations

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

    mathematical notation and code

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    findpost
    -0.83
    IsContent
    -0.68
    DoubleQuotes
    -0.67
     NSCoder
    -0.64
     Monfieur
    -0.63
     >=",
    -0.62
     Houſe
    -0.62
     estekak
    -0.60
    +#+#
    -0.60
    /*---
    -0.59
    POSITIVE LOGITS
    críbete
    0.47
     esternos
    0.47
     resourceCulture
    0.47
    InvalidProtocol
    0.46
     linkovi
    0.45
     阅读
    0.44
    PasswordField
    0.44
    }{
    0.43
    цезда
    0.43
    right
    0.43
    Activations Density 0.027%

    No Known Activations