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 - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 9589
    Prev
    Next
    INDEX
    Explanations

    sections of text that contain mathematical or technical content

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     başına
    -0.56
     Y
    -0.55
     faudra
    -0.53
     x
    -0.52
     it
    -0.51
    LEADING
    -0.49
    tele
    -0.49
     X
    -0.47
     Key
    -0.46
    randn
    -0.46
    POSITIVE LOGITS
    DoubleQuotes
    7.83
    BeginContext
    1.46
    MessageTagHelper
    1.36
     препратки
    1.34
     Baillargeon
    1.30
     الحره
    1.28
     ModelExpression
    1.27
    RenderAtEndOf
    1.27
    PerformLayout
    1.25
    tagHelperRunner
    1.25
    Activations Density 0.005%

    No Known Activations