© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 10436
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs related to database operations and data manipulation

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

    Code-related terms and names

    np_acts-logits-general · gemini-2.0-flash

    numerical expressions with dollar signs

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ChromeDriver
    -0.67
    تقاوى
    -0.65
    tagHelperRunner
    -0.61
    InitVars
    -0.59
    Personendaten
    -0.59
    ^(@)
    -0.58
    momix
    -0.55
    Copyright
    -0.54
     ErrIntOverflow
    -0.54
     Dorothea
    -0.54
    POSITIVE LOGITS
    urlpatterns
    0.58
    XmlAccessorType
    0.52
     world
    0.49
    taciones
    0.49
    tableFuture
    0.48
    حوالہ
    0.47
    bewerken
    0.47
     global
    0.47
     asal
    0.47
    glUniform
    0.46
    Activations Density 0.039%

    No Known Activations