© 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. 12600
    Prev
    Next
    INDEX
    Explanations

    numerical references or citations within a text, particularly those related to cases or events

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

    years and dates written in numeric format (especially those containing digits like 19__ and 193_).

    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
    falgar
    -0.33
     fVar
    -0.32
     ویکی‌پدی
    -0.32
     компьютер
    -0.30
    COMPUTER
    -0.30
    zugehen
    -0.29
     Opiniones
    -0.28
    EFAULT
    -0.28
     fausse
    -0.28
    RTGC
    -0.28
    POSITIVE LOGITS
     Depression
    0.88
     depression
    0.78
    Depression
    0.74
    depression
    0.73
     WPA
    0.68
    WPA
    0.64
     FDR
    0.62
    
    0.61
     Meksiku
    0.61
     Works
    0.58
    Activations Density 0.421%

    No Known Activations