© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 10056
    Prev
    Next
    INDEX
    Explanations

    references to art and artistic entities

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

    "Art" followed by related concepts or companies

    np_acts-logits-general · gemini-2.0-flash

    art followed by price, form, or movement

    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
    SourceChecksum
    -1.03
    expandindo
    -0.90
     ویکی‌پدیا
    -0.87
     виправивши
    -0.83
    MigrationBuilder
    -0.83
     Waray
    -0.83
    +#+#
    -0.82
    ParallelGroup
    -0.81
    IUrlHelper
    -0.79
    UnsafeEnabled
    -0.79
    POSITIVE LOGITS
     deco
    0.66
    form
    0.64
     Deco
    0.61
    fully
    0.61
     nouveau
    0.59
    ficial
    0.59
    forms
    0.58
    fact
    0.57
     form
    0.56
     déco
    0.56
    Activations Density 0.054%

    No Known Activations