© 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. 31-GEMMASCOPE-RES-16K
    11. 1709
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific analysis and evaluation in various contexts

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

    words with Latin or scientific prefixes and suffixes, particularly in academic or technical contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    words with the suffix "-ative" or morphologically similar patterns that form adjectives or nouns describing qualities or states.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queryInterface
    -0.66
     AssemblyTitle
    -0.56
     fieldNum
    -0.55
     propOrder
    -0.55
     nakalista
    -0.55
     <>",
    -0.54
     հղումներ
    -0.53
     kasarigan
    -0.53
     informée
    -0.49
    بوابة
    -0.49
    POSITIVE LOGITS
     mijne
    0.54
     dezelve
    0.45
     gevol
    0.44
    ésult
    0.43
    ations
    0.41
    ative
    0.39
     vrijwilli
    0.39
    ation
    0.38
     leerlingen
    0.38
    criminator
    0.37
    Activations Density 0.986%

    No Known Activations