© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 3435
    Prev
    Next
    INDEX
    Explanations

    references to statistical models and estimators in research literature

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

    legal and academic citations with publication years and page numbers.

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

    citations and bibliographic references in academic and legal documents.

    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
    Externé
    -0.60
    WithIOException
    -0.49
    ChromeDriver
    -0.49
    featureID
    -0.48
    SqlClient
    -0.48
    batore
    -0.46
    TSCA
    -0.45
    ulemon
    -0.45
    ंदीखरीदारी
    -0.44
     CGSize
    -0.44
    POSITIVE LOGITS
     N
    0.88
    nonumber
    0.69
     Nathan
    0.69
    N
    0.68
     nitrogen
    0.68
     numpy
    0.66
     न
    0.61
     ந
    0.61
     North
    0.60
     ন
    0.60
    Activations Density 1.731%

    No Known Activations