© 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. 382
    Prev
    Next
    INDEX
    Explanations

    meta tags related to web content specifications

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

    HTML meta tag attributes related to content type specifications

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

    http-equiv or chemical formulas

    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
    raw
    -0.54
    (
    -0.45
    ाव
    -0.45
     dobro
    -0.44
     mest
    -0.44
     raw
    -0.43
    king
    -0.42
     deven
    -0.42
     touché
    -0.41
    ั้ง
    -0.41
    POSITIVE LOGITS
    equiv
    1.12
     propOrder
    1.07
    StoryboardSegue
    0.97
    IntoConstraints
    0.89
    EDEFAULT
    0.88
     NUKAT
    0.87
     pinulongan
    0.86
    SequentialGroup
    0.83
    Datuak
    0.82
     betweenstory
    0.82
    Activations Density 0.008%

    No Known Activations