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

    Neuronpedia

    APICircuit 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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43219
    Prev
    Next
    INDEX
    Explanations

    elements related to software terminology and programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,
    -0.49
     M
    -0.47
     list
    -0.46
     In
    -0.46
    …
    -0.45
     in
    -0.44
     del
    -0.44
     Rest
    -0.43
     List
    -0.43
     
    -0.43
    POSITIVE LOGITS
    تقاوى
    1.09
     reaſon
    0.82
     Савезне
    0.80
    новниш
    0.79
     nahilalakip
    0.78
     itſelf
    0.78
     unſ
    0.76
     ſch
    0.76
    Portale
    0.75
    новништво
    0.75
    Activations Density 0.005%

    No Known Activations