© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 1913
    Prev
    Next
    INDEX
    Explanations

    references to historical events and entities associated with Ireland and its regions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns and geographic locations, particularly place names and institutional titles.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Polri
    -0.44
     Turquía
    -0.42
     conclusión
    -0.41
     asequ
    -0.41
    tagHelperRunner
    -0.40
     mukana
    -0.39
     salpic
    -0.38
     acompañado
    -0.38
     Zoltán
    -0.38
     zvíř
    -0.37
    POSITIVE LOGITS
     North
    0.82
     South
    0.82
     Newark
    0.81
     Lake
    0.77
     Port
    0.75
     East
    0.74
     Mount
    0.74
     West
    0.74
     San
    0.73
     Los
    0.73
    Activations Density 1.904%

    No Known Activations