© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 9724
    Prev
    Next
    INDEX
    Explanations

    comparative and quantitative expressions related to scientific observations and outcomes

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

    Comparative or superlative adjectives

    np_acts-logits-general · gemini-2.0-flash

    comparative degree or specification

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.68
     оригіналу
    -0.64
     beſte
    -0.64
    AndEndTag
    -0.63
     autorytatywna
    -0.63
    makeConstraints
    -0.63
    MLLoader
    -0.63
    ⟬
    -0.61
     препратки
    -0.61
    iſchen
    -0.61
    POSITIVE LOGITS
     chez
    0.98
     in
    0.79
     bei
    0.78
     for
    0.71
    对于
    0.69
    สำหรับ
    0.68
     ở
    0.63
     بالنسبة
    0.62
     beim
    0.62
     đối
    0.61
    Activations Density 2.582%

    No Known Activations