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. 20-GEMMASCOPE-RES-16K
    6. 1891
    Prev
    Next
    INDEX
    Explanations

    variations of whitespace or newlines in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     же
    -0.45
     ser
    -0.43
    則
    -0.43
     por
    -0.42
     $\
    -0.42
     art
    -0.41
     !
    -0.41
     ар
    -0.41
    </strong>
    -0.41
     const
    -0.41
    POSITIVE LOGITS
     كومونز
    0.97
    mybatisplus
    0.87
    tagHelperRunner
    0.86
    setVerticalGroup
    0.83
    WebVitals
    0.82
     Chwiliwch
    0.82
     itſelf
    0.81
    />";
    0.80
    ArgumentParser
    0.77
    principalColumn
    0.76
    Activations Density 0.590%

    No Known Activations