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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 14743
    Prev
    Next
    INDEX
    Explanations

    references to specific scientific terms and names

    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
     NSCoder
    -0.62
    -------------</
    -0.55
    expects
    -0.55
    شهاد
    -0.53
    RunWith
    -0.53
    Portale
    -0.52
     تضيفلها
    -0.51
    citation
    -0.50
     للاسماء
    -0.50
     OnTrigger
    -0.48
    POSITIVE LOGITS
    ̯
    0.78
    ̍t
    0.56
    Kjelder
    0.54
     publiques
    0.54
     concer
    0.53
     Audiodateien
    0.53
    ux
    0.52
    utenant
    0.52
    象
    0.51
    Chham
    0.50
    Activations Density 0.325%

    No Known Activations