© 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. 19-GEMMASCOPE-RES-16K
    11. 15595
    Prev
    Next
    INDEX
    Explanations

    references to Swedish institutions, councils, or frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Offisielt
    -0.55
     pleaſure
    -0.54
     houſe
    -0.51
     Zang
    -0.49
     igång
    -0.49
     heuer
    -0.48
     Potomac
    -0.48
    ligg
    -0.48
     مشين
    -0.48
    scribers
    -0.48
    POSITIVE LOGITS
     Swedish
    1.37
    Swedish
    1.25
     Sweden
    1.24
     swedish
    1.18
    Sweden
    1.16
     Scandinavian
    1.14
     Nordic
    1.13
    Nordic
    1.07
    瑞典
    1.06
     Stockholm
    1.06
    Activations Density 0.494%

    No Known Activations