© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 4105
    Prev
    Next
    INDEX
    Explanations

    references to uncertainty, origins, and investigation into the source of information

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

    source or origin

    np_acts-logits-general · gemini-2.0-flash

    source or origin

    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
    exitRule
    -0.53
     بيها
    -0.49
     Wicidata
    -0.49
    AndEndTag
    -0.49
     prévue
    -0.48
     NSCoder
    -0.48
    RegressionTest
    -0.48
    MemoryWarning
    -0.45
    Опис
    -0.45
     Económica
    -0.44
    POSITIVE LOGITS
     source
    1.91
     origin
    1.81
     sources
    1.65
     origins
    1.52
    source
    1.52
    origin
    1.49
     Origin
    1.47
     Source
    1.47
    Origin
    1.45
     origen
    1.43
    Activations Density 0.612%

    No Known Activations