© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1958
    Prev
    Next
    INDEX
    Explanations

    instances of the word "la" and its variations in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.95
    /*---
    -0.94
    Datuak
    -0.91
    ISupport
    -0.91
     AssemblyTitle
    -0.87
    Portail
    -0.86
     étoient
    -0.83
    /*
    -0.83
    +#+
    -0.83
    MemoryWarning
    -0.83
    POSITIVE LOGITS
     la
    2.45
    la
    2.44
    LA
    1.98
     La
    1.97
     LA
    1.93
    La
    1.92
    ла
    1.46
    Ла
    1.44
     ла
    1.44
     Ла
    1.29
    Activations Density 0.124%

    No Known Activations