© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15821
    Prev
    Next
    INDEX
    Explanations

    patterns of numerical data or references to experiments and results in a scientific context

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

    year citations in academic papers, particularly focusing on years in parentheses like "(1980)" or "(2002)".

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

    years in academic citations (four-digit numbers within parentheses in reference lists).

    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
    LookAnd
    -0.49
    invokeLater
    -0.44
     فريبيس
    -0.43
    новништво
    -0.40
    RTEE
    -0.37
     NSCoder
    -0.33
    makeConstraints
    -0.32
    oredCriteria
    -0.32
     CanadaChoose
    -0.32
    msgTypes
    -0.31
    POSITIVE LOGITS
     affect
    2.14
     affecting
    2.11
    affect
    2.09
     affects
    2.09
     AFFECT
    1.95
    Affect
    1.90
     affected
    1.88
     Affect
    1.88
     Affecting
    1.87
     Affects
    1.85
    Activations Density 0.550%

    No Known Activations