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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3250
    Prev
    Next
    INDEX
    Explanations

    references to additional elements or components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.81
     Eſ
    -0.72
     houſe
    -0.66
     Houſe
    -0.65
     Diſ
    -0.64
    titu
    -0.63
     étoient
    -0.61
     Reſ
    -0.60
     viſ
    -0.59
     preſent
    -0.59
    POSITIVE LOGITS
     extra
    1.26
     additional
    1.17
     tambahan
    1.13
    additional
    1.07
     added
    1.06
     zusätzlichen
    1.01
    extra
    1.00
     thêm
    0.97
     Additional
    0.97
     ADDITIONAL
    0.97
    Activations Density 0.595%

    No Known Activations