© 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. 9859
    Prev
    Next
    INDEX
    Explanations

    specific symbols or formatting elements in the text

    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
     שוליים
    -0.58
     فريبيس
    -0.54
    Eloquent
    -0.54
    CppMethod
    -0.50
    iNdEx
    -0.50
    ProgressHUD
    -0.48
    EndContext
    -0.46
     estekak
    -0.44
    ImageContext
    -0.43
    通販
    -0.43
    POSITIVE LOGITS
     purpoſe
    0.52
     getopt
    0.52
    ecord
    0.52
    lectric
    0.49
    rizona
    0.49
    xcc
    0.49
    ducation
    0.49
    nivers
    0.49
    nder
    0.48
     RouterModule
    0.48
    Activations Density 0.396%

    No Known Activations