© 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. 25-GEMMASCOPE-RES-16K
    11. 2341
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions or notation involving operators and variables

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Moraes
    -0.59
     Fizz
    -0.57
    Datuak
    -0.54
     Firth
    -0.51
    
    -0.51
    Diweddarwch
    -0.51
    ंदीखरीदारी
    -0.50
     atmospheres
    -0.50
    atility
    -0.50
    Sucesor
    -0.50
    POSITIVE LOGITS
    mathbf
    1.71
    boldsymbol
    0.87
    <b>
    0.68
     Woodruff
    0.59
     Bous
    0.57
    <strong>
    0.57
    modelBuilder
    0.57
    GraphicsUnit
    0.56
    ConstraintMaker
    0.56
    //
    0.56
    Activations Density 0.240%

    No Known Activations