© 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. 1-GEMMASCOPE-RES-16K
    11. 2684
    Prev
    Next
    INDEX
    Explanations

    references to training and education in various contexts, especially regarding soil and agriculture

    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
     Exactos
    -0.56
    enumi
    -0.50
    transQ
    -0.47
    oa̍t
    -0.46
    indrome
    -0.45
    homonymie
    -0.44
    állítás
    -0.44
    ⋙
    -0.44
     voorkomen
    -0.42
     inalámb
    -0.42
    POSITIVE LOGITS
    ContentLoaded
    0.49
    残
    0.48
     ProtoMessage
    0.47
     Veteran
    0.46
    entieth
    0.46
     training
    0.45
    internalType
    0.44
     Wel
    0.43
     Training
    0.43
    殘
    0.43
    Activations Density 0.241%

    No Known Activations