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. 22-GEMMASCOPE-RES-16K
    6. 14131
    Prev
    Next
    INDEX
    Explanations

    phrases related to cutting-edge technology and advanced manufacturing processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.82
    tagHelperRunner
    -0.78
    تقاوى
    -0.68
    contentLoaded
    -0.67
    expandindo
    -0.65
     transfieras
    -0.60
    ValueGeneration
    -0.58
    írus
    -0.57
     autorytatywna
    -0.56
    HtmlAttribute
    -0.56
    POSITIVE LOGITS
     state
    2.05
     cutting
    1.89
    state
    1.77
     advanced
    1.62
    cutting
    1.59
    Cutting
    1.55
     Cutting
    1.53
     modern
    1.41
    advanced
    1.32
     STATE
    1.32
    Activations Density 0.373%

    No Known Activations