© 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. 1-GEMMASCOPE-RES-16K
    6. 9055
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or entities, particularly those related to notable people or brands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    клопе
    -0.66
    例句
    -0.65
     Pele
    -0.64
    expandindo
    -0.63
     Италијани
    -0.62
     lek
    -0.62
     Lek
    -0.62
     Siva
    -0.60
     Wittenberg
    -0.59
     NKC
    -0.58
    POSITIVE LOGITS
     MainAxisSize
    0.72
     Reggie
    0.68
     Langer
    0.64
    ulaski
    0.64
    ⋙
    0.63
     Franklin
    0.62
    Franklin
    0.61
    enheim
    0.61
     Crusade
    0.61
     Schindler
    0.60
    Activations Density 2.856%

    No Known Activations