© 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. 11529
    Prev
    Next
    INDEX
    Explanations

    noteworthy instructions or notes in a technical context

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

    formatting elements and structural indicators in documents such as section headers, notes, and important information callouts.

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

    periods and sentence endings that mark the conclusion of instructional or explanatory statements.

    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
     للاسماء
    -0.79
     Normdatei
    -0.77
     كومونز
    -0.74
    Hentet
    -0.74
     ModelExpression
    -0.73
     AssemblyCompany
    -0.72
    évaluateur
    -0.71
    
    -0.69
     betweenstory
    -0.69
    TestingModule
    -0.67
    POSITIVE LOGITS
     NOTE
    1.30
     note
    1.30
    Note
    1.29
    NOTE
    1.28
     Note
    1.28
    note
    1.08
    注意
    1.08
     WARNING
    1.05
    WARNING
    1.05
     warning
    1.02
    Activations Density 0.368%

    No Known Activations