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 Post
    5. 12-GEMMASCOPE-RES-1M
    6. 44
    Prev
    Next
    INDEX
    Explanations

    identified types and data structures commonly used in programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    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
     itſelf
    -1.16
     myſelf
    -1.02
     Efq
    -1.02
     Theſe
    -1.02
    帖最后由
    -0.96
    AddTagHelper
    -0.95
    SpringBootTest
    -0.94
     Exacts
    -0.93
     themſelves
    -0.92
     faſt
    -0.91
    POSITIVE LOGITS
     tra
    0.58
     his
    0.52
     His
    0.51
     e
    0.47
     dan
    0.46
     die
    0.45
     con
    0.45
     res
    0.44
     A
    0.44
     Tra
    0.44
    Activations Density 0.001%

    No Known Activations