© 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. 2-GEMMASCOPE-RES-16K
    11. 4629
    Prev
    Next
    INDEX
    Explanations

    the word "through" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personendaten
    -0.90
    GEBURTSDATUM
    -0.71
     kasarigan
    -0.67
    BagConstraints
    -0.66
    IsMutable
    -0.63
    rungsseite
    -0.62
    Билгалдахарш
    -0.58
     يتيمه
    -0.57
    الحياه
    -0.57
    يكب
    -0.57
    POSITIVE LOGITS
     undergo
    0.72
     underwent
    0.67
     undergone
    0.66
     undergoes
    0.64
     undergoing
    0.60
     sufrió
    0.43
     sufrido
    0.43
     sufre
    0.41
     seguito
    0.41
    經歷
    0.40
    Activations Density 0.303%

    No Known Activations