Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 3464
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations relevant to physical theories or constraints

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    хьтан
    -0.87
     незавершена
    -0.83
     uska
    -0.76
     mxArray
    -0.74
    mybatisplus
    -0.74
     CreateTagHelper
    -0.73
     فريبيس
    -0.72
     насељу
    -0.68
     урна
    -0.67
    httphttps
    -0.66
    POSITIVE LOGITS
    Osob
    0.48
    ตร์
    0.45
    尉
    0.44
     built
    0.44
     Built
    0.42
     recevez
    0.42
     BUILT
    0.42
    Built
    0.42
     contactez
    0.41
     Legge
    0.41
    Activations Density 1.491%

    No Known Activations