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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 7649
    Prev
    Next
    INDEX
    Explanations

    occurrences of the text indicating the beginning or end of a document or section

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fieldNum
    -0.79
    tagHelper
    -0.79
    mybatisplus
    -0.75
     تضيفلها
    -0.71
    AutoScale
    -0.69
     CreateTagHelper
    -0.67
    awtextra
    -0.65
    Conclusie
    -0.64
    ercises
    -0.64
    }")
    
    -0.63
    POSITIVE LOGITS
    terase
    0.54
    chaun
    0.52
    Palindrome
    0.49
    ↻
    0.47
    стра
    0.45
    Rourke
    0.44
     Erişim
    0.44
    RegisterType
    0.44
     متعلقه
    0.44
    MetaObject
    0.43
    Activations Density 0.041%

    No Known Activations