© 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-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8753
    Prev
    Next
    INDEX
    Explanations

    specific geographical and cultural terms related to Wales

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

    Welsh places or mythology

    np_acts-logits-general · gemini-2.0-flash

    Welsh and Wales related content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.70
    Geplaatst
    -0.69
    ConstraintMaker
    -0.68
    AsUp
    -0.61
    TargetException
    -0.59
     للمعارف
    -0.59
     Missouri
    -0.58
     Templates
    -0.55
     ſeine
    -0.54
    NameInMap
    -0.54
    POSITIVE LOGITS
     Welsh
    0.88
    Welsh
    0.80
     Wales
    0.71
     Cardiff
    0.68
    Wales
    0.66
    Cardiff
    0.64
     Swansea
    0.56
     useRouter
    0.52
    Newport
    0.51
     Newport
    0.49
    Activations Density 0.246%

    No Known Activations