© 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. 399
    Prev
    Next
    INDEX
    Explanations

    elements related to data structure definitions and properties

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

    code-related terms and structures in programming or software definitions

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

    code followed by terminators

    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
    '])){
    -1.03
    "],
    -0.96
    ++
    -0.88
    "];
    -0.88
    }]
    -0.87
    ']))
    -0.85
    '){
    -0.85
    '):
    -0.84
    ')){
    -0.84
    ')):
    -0.84
    POSITIVE LOGITS
    .
    0.52
    ANTLR
    0.48
     imitating
    0.47
     refleja
    0.45
     marcó
    0.45
     näin
    0.44
     realises
    0.42
    хьтан
    0.41
    Putting
    0.41
     tourmaline
    0.41
    Activations Density 0.043%

    No Known Activations