© 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-2-9B
    7. Residual Stream - 16k
    9. 38-GEMMASCOPE-RES-16K
    11. 7178
    Prev
    Next
    INDEX
    Explanations

    references to the word "New," particularly in relation to locations or contexts associated with New York

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PeEnEo
    -0.45
    autaire
    -0.42
     novità
    -0.39
     negar
    -0.36
     conviene
    -0.36
     embora
    -0.36
     mới
    -0.34
    ข่าว
    -0.34
     newly
    -0.34
     مض
    -0.34
    POSITIVE LOGITS
     york
    0.94
    york
    0.82
    tonsoft
    0.80
     York
    0.80
     zealand
    0.79
     Zealand
    0.78
    York
    0.75
    foundland
    0.75
    sworth
    0.73
    comer
    0.71
    Activations Density 0.231%

    No Known Activations