© 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. 8-GEMMASCOPE-RES-16K
    6. 10215
    Prev
    Next
    INDEX
    Explanations

    the definite article "the" and its contextual usage in various phrases

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portale
    -0.78
    žku
    -0.69
    shadowOpacity
    -0.67
    ātu
    -0.66
    archiviato
    -0.66
    ImageContext
    -0.64
     مشين
    -0.62
    sphin
    -0.61
    pleen
    -0.60
     Oru
    -0.57
    POSITIVE LOGITS
     BY
    1.10
     oleh
    1.10
     by
    1.07
    by
    1.03
    By
    1.03
     By
    1.01
    BY
    0.91
     Byers
    0.78
    ByDate
    0.76
    ByID
    0.75
    Activations Density 0.163%

    No Known Activations