© 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-2-2B
    7. Residual Stream - 16k
    9. 5-GEMMASCOPE-RES-16K
    11. 7217
    Prev
    Next
    INDEX
    Explanations

    instances of the word "he" and words indicating time during an event

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tartalomajánló
    -1.05
    findpost
    -0.95
     سكانية
    -0.89
    WriteBarrier
    -0.86
    
    -0.85
    InputTagHelper
    -0.81
    WithIOException
    -0.80
    انيف
    -0.79
    ✨:
    -0.78
    #+#
    -0.76
    POSITIVE LOGITS
    ั
    0.52
     féminin
    0.47
     Krakowie
    0.46
     bağlı
    0.46
    Kit
    0.45
     wanita
    0.44
    キット
    0.44
    schule
    0.43
     urmă
    0.43
    c
    0.43
    Activations Density 0.371%

    No Known Activations