© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1753
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns referring to multiple subjects

    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
    addNode
    -0.49
    етка
    -0.46
     gully
    -0.44
     feroit
    -0.43
     curve
    -0.43
    fehlung
    -0.42
    vgg
    -0.42
     shovel
    -0.42
     Bite
    -0.42
    🟨
    -0.41
    POSITIVE LOGITS
     their
    3.28
    their
    2.81
    Their
    2.77
     Their
    2.59
     THEIR
    2.30
     jejich
    2.22
    他们的
    2.16
    他們的
    2.16
     leurs
    2.16
     leur
    2.16
    Activations Density 0.174%

    No Known Activations