© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 8454
    Prev
    Next
    INDEX
    Explanations

    phrases related to visual representation and positioning

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

    Code snippets and foreign language text

    np_acts-logits-general · gemini-2.0-flash

    on or at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.50
     zarówno
    -0.47
     chré
    -0.47
     professionali
    -0.46
     Соб
    -0.45
     Chel
    -0.44
     ogóle
    -0.43
    </strong>
    -0.42
     origines
    -0.42
    Stock
    -0.41
    POSITIVE LOGITS
    TypedDataSet
    0.79
    SequentialGroup
    0.79
    UIControlState
    0.73
     FormsModule
    0.72
    ArgumentParser
    0.72
     BorderRadius
    0.70
     ostavi
    0.69
    SOUNDBITE
    0.68
    RectangleBorder
    0.68
    extAlignment
    0.67
    Activations Density 0.025%

    No Known Activations