© 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. 4355
    Prev
    Next
    INDEX
    Explanations

    the word "Their" and its variants, indicating a focus on possession or belonging

    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
     Extension
    -0.57
     extension
    -0.57
     extensions
    -0.56
     EXTENSION
    -0.52
    Extension
    -0.51
    ressee
    -0.50
    extension
    -0.50
     pegged
    -0.49
    constru
    -0.48
    EXTENSION
    -0.47
    POSITIVE LOGITS
     His
    0.76
     Their
    0.76
     Its
    0.69
    His
    0.66
    Their
    0.60
    Its
    0.53
     Your
    0.52
     tartalomajánló
    0.51
     Его
    0.51
     authorities
    0.51
    Activations Density 0.078%

    No Known Activations