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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 5963
    Prev
    Next
    INDEX
    Explanations

    elements associated with modern and minimalist design aesthetics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Prepositions and articles

    np_acts-logits-general · gemini-2.0-flash

    styles and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    tvguidetime
    -0.85
     snippetHide
    -0.72
    WindowConstants
    -0.70
     архивлан
    -0.65
     exceptionnelle
    -0.59
    neté
    -0.57
     étrangère
    -0.57
    #+#
    -0.57
    kijken
    -0.57
     pleaſure
    -0.56
    POSITIVE LOGITS
     rustic
    1.08
     minimalist
    1.06
     minimalistic
    1.03
     retro
    1.02
     edgy
    1.00
     earthy
    0.95
     sporty
    0.92
     modern
    0.92
     whimsical
    0.88
     casual
    0.88
    Activations Density 0.289%

    No Known Activations