© 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. 23-GEMMASCOPE-RES-16K
    11. 2364
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a return or movement back to a previous state or location

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Sure
    -0.36
    One
    -0.34
     Viena
    -0.34
     Pohl
    -0.34
    onych
    -0.32
     sure
    -0.32
    urcht
    -0.31
    టు
    -0.31
     dumne
    -0.31
     One
    -0.31
    POSITIVE LOGITS
     semula
    0.73
     kembali
    0.71
    PageRoute
    0.68
    posedge
    0.67
    again
    0.66
    原始内容存档于
    0.65
     wró
    0.65
     again
    0.64
    ReusableCell
    0.63
     Returning
    0.62
    Activations Density 0.259%

    No Known Activations