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. 10-GEMMASCOPE-RES-16K
    6. 11779
    Prev
    Next
    INDEX
    Explanations

    references to the UK and related entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueGeneration
    -0.75
    poin
    -0.74
    sendMail
    -0.74
     ActionListener
    -0.72
    Примітки
    -0.72
     Commemor
    -0.71
     dress
    -0.69
     MAZ
    -0.69
    <h3>
    -0.68
    ็จ
    -0.68
    POSITIVE LOGITS
     Brito
    1.19
     Britton
    1.09
     Britain
    1.08
    britannien
    1.07
     BRIT
    1.02
    Brit
    1.00
    -£
    1.00
     Brit
    0.97
     UK
    0.96
     Unido
    0.96
    Activations Density 0.075%

    No Known Activations