© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 8
    Prev
    Next
    INDEX
    Explanations

    initial tokens or markers that indicate the beginning of sections or segments in a text

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

    the beginning of text or document prompts

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

    prepositions and conjunctions

    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
     proyecto
    -0.46
     brosse
    -0.46
     femininas
    -0.45
     malheureux
    -0.44
    šť
    -0.43
     finas
    -0.43
     normes
    -0.43
     inmediato
    -0.42
     homens
    -0.42
     direção
    -0.42
    POSITIVE LOGITS
    AutoField
    1.37
    ...");
    0.76
    `,
    0.71
    forChild
    0.68
    odeon
    0.67
    extAlignment
    0.66
    ſelf
    0.65
    <!--[
    0.65
     itſelf
    0.64
     bezeichneter
    0.64
    Activations Density 0.004%

    No Known Activations