© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 6544
    Prev
    Next
    INDEX
    Explanations

    locations and geographical descriptors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     despedida
    -0.49
    parsedMessage
    -0.48
    einander
    -0.47
    őzés
    -0.47
     degradation
    -0.45
    üyada
    -0.45
    BASELINE
    -0.44
     Мексичка
    -0.41
     Betracht
    -0.41
    RSC
    -0.41
    POSITIVE LOGITS
     located
    1.41
     situated
    1.29
     Located
    1.16
    located
    1.10
    Located
    1.08
     Situated
    1.03
     situé
    0.98
    Situated
    0.96
     situés
    0.95
     situado
    0.93
    Activations Density 0.435%

    No Known Activations