© 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-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 5039
    Prev
    Next
    INDEX
    Explanations

    references to locations and entities related to Boston

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Niger
    -0.37
    jooq
    -0.35
     украин
    -0.34
     Yukon
    -0.34
     Ukrainian
    -0.33
     تانيه
    -0.33
     venezolano
    -0.33
     ucran
    -0.32
     Padang
    -0.32
     Iraqi
    -0.32
    POSITIVE LOGITS
     Boston
    1.92
    Boston
    1.80
     Massachusetts
    1.78
    Massachusetts
    1.69
     BOSTON
    1.65
     boston
    1.63
    boston
    1.54
    BOSTON
    1.53
     MASSACHUSETTS
    1.38
     Harvard
    1.27
    Activations Density 0.445%

    No Known Activations