© 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. 9-GEMMASCOPE-RES-16K
    11. 8676
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate locations and spatial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     мәкал
    -0.56
     Мексичка
    -0.55
     Grüsse
    -0.52
    хьтан
    -0.51
    Autoritní
    -0.50
     ainfi
    -0.49
     purpoſe
    -0.49
    einander
    -0.48
     autorytatywna
    -0.47
    parsedMessage
    -0.47
    POSITIVE LOGITS
     located
    1.50
     situated
    1.26
     Located
    1.25
    Located
    1.18
    located
    1.18
     situés
    1.09
     Situated
    1.08
     situé
    1.01
     расположен
    0.99
    Situated
    0.98
    Activations Density 0.487%

    No Known Activations