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. 2840
    Prev
    Next
    INDEX
    Explanations

    concepts and discussions related to technology and software development

    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
     &___
    -0.60
    arschijnlijk
    -0.58
    それと
    -0.58
    windowFixed
    -0.57
    ÓW
    -0.54
    ---|---|
    -0.54
    ->___
    -0.51
    iformis
    -0.51
    HasAnnotation
    -0.50
    usitis
    -0.48
    POSITIVE LOGITS
     where
    3.96
    where
    3.45
    Where
    2.89
     Where
    2.80
     donde
    2.79
     où
    2.73
     WHERE
    2.62
     где
    2.44
     wherein
    2.42
    donde
    2.36
    Activations Density 1.584%

    No Known Activations