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. 1-GEMMASCOPE-RES-16K
    6. 2860
    Prev
    Next
    INDEX
    Explanations

    words related to substances or components involved in chemical reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     étoit
    -0.64
     Infór
    -0.57
     feroit
    -0.56
     auroit
    -0.54
     desmotivaciones
    -0.52
    ambién
    -0.52
     Vermögen
    -0.51
     pouvoit
    -0.48
    colgante
    -0.48
     navideño
    -0.48
    POSITIVE LOGITS
    izer
    2.17
    iz
    2.09
    ize
    2.06
    izers
    1.88
    IZ
    1.86
    izes
    1.85
    IZE
    1.80
    IZER
    1.77
    izing
    1.73
    iza
    1.54
    Activations Density 0.254%

    No Known Activations