Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 14169
    Prev
    Next
    INDEX
    Explanations

    instances of the term "using System" and related namespaces in programming contexts

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

    after periods in file paths or code

    np_acts-logits-general · gemini-2.0-flash

    .ServiceModel dlls and programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addCriterion
    -0.50
     комби
    -0.48
    melidir
    -0.46
    Gemeinden
    -0.46
    役割
    -0.46
     kasarigan
    -0.44
    asilan
    -0.44
    ContentAlignment
    -0.44
    تقاوى
    -0.43
     Visit
    -0.42
    POSITIVE LOGITS
    Linq
    0.98
    Text
    0.90
    Collections
    0.86
    Threading
    0.78
    Web
    0.75
    Globalization
    0.72
    Runtime
    0.71
    Diagnostics
    0.69
    Reflection
    0.69
    IO
    0.67
    Activations Density 0.023%

    No Known Activations