© 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. 2099
    Prev
    Next
    INDEX
    Explanations

    references to adoption and legal procedures

    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
    peq
    -0.60
    ValueStyle
    -0.57
     springfox
    -0.54
    invokeLater
    -0.54
     estimés
    -0.53
     CreateTagHelper
    -0.52
    %^
    -0.52
    MessageOf
    -0.50
    colazione
    -0.49
    וויק
    -0.49
    POSITIVE LOGITS
     foster
    1.41
     adoption
    1.41
     Adoption
    1.38
     adoptive
    1.31
     adop
    1.30
    Adoption
    1.28
     Adop
    1.23
    foster
    1.22
    Adop
    1.20
    adoption
    1.17
    Activations Density 0.580%

    No Known Activations