Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 12566
    Prev
    Next
    INDEX
    Explanations

    terms related to complementary relationships or enhancements between concepts

    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
    czyn
    -0.33
     ابت
    -0.33
    ItemLayout
    -0.32
    RegressionTest
    -0.31
    万人
    -0.30
     Waterproof
    -0.30
    }]{
    -0.29
    delwed
    -0.29
    ufact
    -0.29
    ürger
    -0.29
    POSITIVE LOGITS
     complement
    1.20
     complements
    1.13
     Complement
    1.12
    Complement
    1.09
     complementary
    1.09
    complement
    1.05
     complementa
    1.05
     compliment
    1.04
     Complementary
    1.00
     complemented
    0.97
    Activations Density 0.540%

    No Known Activations