© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3615
    Prev
    Next
    INDEX
    Explanations

    verbs related to modifying or adjusting actions or states

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

    modifier or launch scripts

    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
     seguenti
    -0.56
     particulières
    -0.54
    same
    -0.54
     fondament
    -0.53
     similaire
    -0.53
     dovuto
    -0.53
     giusta
    -0.52
    τως
    -0.52
     actionPerformed
    -0.52
     suivantes
    -0.51
    POSITIVE LOGITS
     efficiently
    0.69
     compul
    0.68
     passively
    0.67
     את
    0.67
    {}",
    0.64
    />";
    0.62
     rigorously
    0.61
     intelligently
    0.60
    Cyfeiriadau
    0.59
     aggressively
    0.59
    Activations Density 0.038%

    No Known Activations