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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8327
    Prev
    Next
    INDEX
    Explanations

    code-related elements, especially focusing on scrolling functionality and element positioning

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

    Scrolling or bottom of content

    np_acts-logits-general · gemini-2.0-flash

    scroll to bottom

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    -0.68
    twimg
    -0.54
    ⓧ
    -0.54
    rungsseite
    -0.53
     plak
    -0.51
    HasForeignKey
    -0.50
     Bete
    -0.49
    migrationBuilder
    -0.49
     placa
    -0.49
    __":
    -0.48
    POSITIVE LOGITS
     botto
    0.61
     bottom
    0.61
    JScrollPane
    0.60
     verticale
    0.60
     scroll
    0.59
    lccn
    0.58
     upward
    0.57
     altitude
    0.55
     écoulé
    0.54
    Bottom
    0.54
    Activations Density 0.390%

    No Known Activations