© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1341
    Prev
    Next
    INDEX
    Explanations

    the presence of underscores and certain mathematical or programming syntax

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

    symbols or formatting characters used in coding or data representation

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

    begin2,

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ď
    -0.47
    Ή
    -0.46
    inty
    -0.44
    ,
    -0.41
     taban
    -0.40
    𝐠
    -0.40
    𝐛
    -0.40
    uric
    -0.40
    Very
    -0.39
    arde
    -0.39
    POSITIVE LOGITS
    <bos>
    3.13
    ’
    1.25
     Савезне
    1.18
    '
    1.17
     disambiguazione
    1.09
    хьтан
    1.01
     виправивши
    0.99
     Paglinawan
    0.95
    Diwedd
    0.94
    begin
    0.94
    Activations Density 0.001%

    No Known Activations