© 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. 3-GEMMASCOPE-RES-16K
    6. 11591
    Prev
    Next
    INDEX
    Explanations

    negative evaluations or criticisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InstrumentedTest
    -0.64
    hythm
    -0.64
    googleapis
    -0.59
     không
    -0.57
     שלא
    -0.57
     nobody
    -0.57
    exitRule
    -0.53
     não
    -0.53
     unable
    -0.52
     tidak
    -0.51
    POSITIVE LOGITS
    protoc
    0.64
    ArgsConstructor
    0.57
    ArgumentParser
    0.54
    ="@+
    0.54
    ruptedException
    0.54
    TintMode
    0.51
    HostException
    0.51
    WebVitals
    0.51
     AssemblyProduct
    0.50
    Бахар
    0.49
    Activations Density 0.396%

    No Known Activations