Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 4279
    Prev
    Next
    INDEX
    Explanations

    references to code structures and variables in programming contexts

    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
     CreateTagHelper
    -1.63
     Савезне
    -1.48
    RenderAtEndOf
    -1.45
     bezeichneter
    -1.44
     betweenstory
    -1.39
     Мексичка
    -1.36
    ConstraintMaker
    -1.35
     transfieras
    -1.33
     <=",
    -1.32
    AddTagHelper
    -1.30
    POSITIVE LOGITS
    </strong>
    0.68
    </em>
    0.65
    <strong>
    0.58
    .
    0.56
    </h2>
    0.55
    ,
    0.55
    ↵↵
    0.54
    <unused61>
    0.52
    <unused62>
    0.51
    <unused63>
    0.50
    Activations Density 0.789%

    No Known Activations