© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 15831
    Prev
    Next
    INDEX
    Explanations

    phrases related to possession or ownership

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Glad
    -0.66
     circuit
    -0.61
     Gladys
    -0.58
    atalyst
    -0.57
     SqlParameter
    -0.57
    Thanking
    -0.56
     circuits
    -0.56
    circuit
    -0.56
    argc
    -0.55
    americas
    -0.55
    POSITIVE LOGITS
     possession
    2.90
     Possession
    2.65
    Poss
    2.64
    possession
    2.46
     Poss
    2.43
     possessed
    2.42
     possess
    2.36
     posses
    2.17
    poss
    2.14
     possesses
    2.09
    Activations Density 0.094%

    No Known Activations