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. 13-GEMMASCOPE-RES-16K
    6. 13829
    Prev
    Next
    INDEX
    Explanations

    parentheses and their usages in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     v
    -0.53
     Mont
    -0.53
     col
    -0.51
     V
    -0.51
     La
    -0.50
    col
    -0.49
     Nam
    -0.49
     Bet
    -0.49
     Sho
    -0.49
    unc
    -0.48
    POSITIVE LOGITS
    +#+#
    1.04
    InjectAttribute
    1.03
     Efq
    1.03
    WriteTagHelper
    1.00
    AddTagHelper
    0.99
    twimg
    0.99
    Tembelea
    0.91
     myſelf
    0.89
     متعلقه
    0.87
     }}$}
    0.86
    Activations Density 0.062%

    No Known Activations