© 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. 2678
    Prev
    Next
    INDEX
    Explanations

    HTML table structures and elements

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

    HTML table tags

    np_acts-logits-general · gemini-2.0-flash

    HTML tag structures

    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
    tvguidetime
    -0.76
    imetsu
    -0.75
    RunWith
    -0.73
    colgroup
    -0.63
     noqa
    -0.63
     المعيارى
    -0.62
     Reichstag
    -0.62
    OpenHelper
    -0.61
    politico
    -0.60
     Svet
    -0.60
    POSITIVE LOGITS
    AccessorTable
    0.89
    <td>
    0.64
     nahilalakip
    0.63
     étrangère
    0.59
    createTextNode
    0.54
    brać
    0.53
    MessageTagHelper
    0.53
     Grüsse
    0.52
    Orléans
    0.51
    </h1>
    0.51
    Activations Density 0.150%

    No Known Activations