Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 8511
    Prev
    Next
    INDEX
    Explanations

    references to Scottish culture and specific locations within Scotland

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

    Scotland or Scottish things

    np_acts-logits-general · gemini-2.0-flash

    Scotland, Scots, Scottish, Scotch

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ǒ
    -0.66
    ENCOD
    -0.65
    ंदीखरीदारी
    -0.65
    rungsseite
    -0.64
    dotenv
    -0.64
    OCR
    -0.62
    Azur
    -0.61
     hashCode
    -0.61
     Albright
    -0.61
     Bekasi
    -0.60
    POSITIVE LOGITS
     Scotland
    1.26
     Scot
    1.23
     Scottish
    1.21
     whisky
    1.19
     Scots
    1.15
    Scotland
    1.14
     Whisky
    1.11
     Scotch
    1.10
    Scottish
    1.06
    whisky
    1.05
    Activations Density 0.559%

    No Known Activations