© 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. 7796
    Prev
    Next
    INDEX
    Explanations

    specific details about geographic locations and fauna

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

    references to marine animals and aquatic wildlife species.

    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
     trigo
    -0.50
     snow
    -0.46
     ski
    -0.45
     hibernate
    -0.45
     Canada
    -0.45
     calefacción
    -0.43
     skiing
    -0.43
     winter
    -0.43
     Winter
    -0.43
     hibern
    -0.42
    POSITIVE LOGITS
     tropical
    1.12
    Tropical
    1.09
     Tropical
    1.08
    tropical
    0.98
     mangrove
    0.93
     tropicales
    0.93
     mangroves
    0.91
     mangoes
    0.89
     machete
    0.89
     tropics
    0.88
    Activations Density 0.388%

    No Known Activations