© 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. 13998
    Prev
    Next
    INDEX
    Explanations

    statements made by individuals, particularly in interviews or news articles

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

    attribution phrases where sources are cited using "told" followed by publication names or news outlets.

    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
     BBC
    -0.45
     apparently
    -0.44
     magazine
    -0.41
    Bloomberg
    -0.40
     newspaper
    -0.40
    con
    -0.40
     Reuters
    -0.40
    nytimes
    -0.40
    aya
    -0.39
     reportedly
    -0.39
    POSITIVE LOGITS
    
    0.96
     kasarigan
    0.85
     invokingState
    0.73
     resourceCulture
    0.71
    migrationBuilder
    0.68
     виправивши
    0.67
    ValueStyle
    0.66
    expandindo
    0.66
     initComponents
    0.65
    Tembelea
    0.63
    Activations Density 0.230%

    No Known Activations