© 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. 377
    Prev
    Next
    INDEX
    Explanations

    mentions of conflicts of interest and related terms

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

    the word "most" indicating emphasis or significance

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

    for the most part

    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
    principalTable
    -0.58
    WebElementEntity
    -0.53
    ampiyon
    -0.52
     imageNamed
    -0.52
    SuppressLint
    -0.52
     verle
    -0.52
     يتيمه
    -0.52
     كومونز
    -0.51
    informatics
    -0.51
     Voyage
    -0.50
    POSITIVE LOGITS
     autorytatywna
    0.63
     restTemplate
    0.59
     pergunt
    0.52
    ungsbedingungen
    0.50
    RectangleBorder
    0.47
     typelib
    0.44
    Interests
    0.43
     chied
    0.43
    dres
    0.43
    AppMethodBeat
    0.42
    Activations Density 0.082%

    No Known Activations