© 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. 22-GEMMASCOPE-RES-16K
    11. 6565
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and conservation efforts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Following prepositions or delimiters

    np_acts-logits-general · gemini-2.0-flash

    New Zealand terms and regions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Nigeria
    -0.56
     Nigerian
    -0.56
    ēju
    -0.54
     thước
    -0.54
    Nigeria
    -0.52
     NgModule
    -0.51
     Borno
    -0.51
     Abuja
    -0.50
     Nigerians
    -0.48
     AssemblyCulture
    -0.48
    POSITIVE LOGITS
     NZ
    1.47
    NZ
    1.44
     Auckland
    1.43
    Auckland
    1.36
     Maori
    1.33
     New
    1.33
     Kiwi
    1.30
     Māori
    1.23
     Christchurch
    1.22
    Kiwi
    1.18
    Activations Density 0.115%

    No Known Activations