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

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 7967
    Prev
    Next
    INDEX
    Explanations

    instances of the word "used" and related contexts

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

    "[Something] used as/in/to/for"

    np_acts-logits-general · gemini-2.0-flash

    used to, as, or for

    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
    LookAnd
    -1.04
    PerformLayout
    -0.80
    出版年
    -0.76
     referrerpolicy
    -0.75
    webElementXpaths
    -0.73
    URLException
    -0.72
    ьаж
    -0.69
    脚注の使い方
    -0.69
    saraba
    -0.69
    InvalidProtocol
    -0.68
    POSITIVE LOGITS
     extensively
    0.85
     sparingly
    0.81
     to
    0.78
     interchangeably
    0.76
     instead
    0.71
     wisely
    0.71
    ในการ
    0.69
     exclusively
    0.64
     for
    0.63
    来
    0.60
    Activations Density 0.526%

    No Known Activations