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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 2497
    Prev
    Next
    INDEX
    Explanations

    phrases related to exploration and analysis

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

    act of exploring

    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
    ing
    -0.74
    espan
    -0.60
     Stad
    -0.59
    .$.
    -0.57
    ING
    -0.54
     
    -0.53
     cục
    -0.52
    djangoproject
    -0.52
     F
    -0.51
    UserScript
    -0.50
    POSITIVE LOGITS
     Expl
    0.93
    Portale
    0.88
    OptionsMenu
    0.82
    Expl
    0.82
     XCTest
    0.81
    tagHelperRunner
    0.79
     magasiner
    0.77
    LORE
    0.76
     Wikis
    0.74
    plor
    0.73
    Activations Density 0.019%

    No Known Activations