© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 4414
    Prev
    Next
    INDEX
    Explanations

    various aspects of scientific research and analysis

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

    ending in "-ations", "-ities", "-tions", "-ings"

    np_acts-logits-general · gemini-2.0-flash

    abstract nouns ending in -ities and -ions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    média
    -0.40
     Stoff
    -0.39
    Toeschouwers
    -0.37
    }}^{(
    -0.37
     cork
    -0.37
     Purse
    -0.37
    unier
    -0.36
     Minerva
    -0.36
    nolia
    -0.36
    coroutine
    -0.36
    POSITIVE LOGITS
     ModelExpression
    0.47
    setVerticalGroup
    0.43
     AssemblyTitle
    0.43
    styleType
    0.42
     okuyayım
    0.42
     kasarigan
    0.42
     Signalez
    0.41
     StatefulWidget
    0.41
    ruptedException
    0.40
     >=",
    0.40
    Activations Density 0.993%

    No Known Activations