© 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-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 13696
    Prev
    Next
    INDEX
    Explanations

    reflexive pronouns and related expressions of self-reference

    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
    ậc
    -0.54
    もしれない
    -0.54
     contextLoads
    -0.53
    expandindo
    -0.48
     Quit
    -0.45
     bise
    -0.45
     snippetHide
    -0.45
    OGND
    -0.43
     estekak
    -0.43
     onStop
    -0.43
    POSITIVE LOGITS
     Keuangan
    0.50
     kvinder
    0.47
     zich
    0.45
     totul
    0.45
     beliau
    0.44
    ándolos
    0.44
    webElementXpaths
    0.43
     conmigo
    0.43
     anaknya
    0.43
     comigo
    0.42
    Activations Density 0.399%

    No Known Activations