© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4335
    Prev
    Next
    INDEX
    Explanations

    references to Irish cultural elements and notable figures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    abetes
    -0.86
    RegressionTest
    -0.83
    kuuta
    -0.81
     Púb
    -0.80
    談社
    -0.75
    EnableWeb
    -0.70
     BorderSide
    -0.67
     quæ
    -0.67
    illaries
    -0.66
    iastes
    -0.66
    POSITIVE LOGITS
     Irish
    1.36
     Ireland
    1.33
    Irish
    1.25
    Ireland
    1.24
     IRELAND
    1.13
     Irishman
    1.13
     irland
    1.09
     Irlanda
    1.08
     irish
    1.08
     Dublin
    1.00
    Activations Density 1.358%

    No Known Activations