© 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. 14-GEMMASCOPE-RES-16K
    11. 13252
    Prev
    Next
    INDEX
    Explanations

    references to individuals, particularly Swedish figures and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    føring
    -0.68
     tjen
    -0.66
     måte
    -0.64
     ferdig
    -0.60
     seier
    -0.60
     samfun
    -0.59
     velg
    -0.58
    ført
    -0.58
     aktivitet
    -0.57
     køb
    -0.57
    POSITIVE LOGITS
     Sweden
    0.92
     Swedish
    0.90
     Uppsala
    0.86
    andinavia
    0.84
    skjaer
    0.83
    Sweden
    0.82
     Scandinavia
    0.79
    kegaard
    0.79
     swedish
    0.79
    Swedish
    0.79
    Activations Density 0.424%

    No Known Activations