© 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. 23-GEMMASCOPE-RES-16K
    6. 14245
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "people."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 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
     Normdatei
    -0.70
    Complete
    -0.64
     Complete
    -0.61
     whiteColor
    -0.54
    __*/
    -0.54
     complete
    -0.53
    complete
    -0.53
     InputDecoration
    -0.51
    extAlignment
    -0.50
    각주
    -0.50
    POSITIVE LOGITS
    opel
    0.61
    haps
    0.57
     lâng
    0.57
    #
    0.55
    Pe
    0.55
     ople
    0.54
     seaborn
    0.54
    principalColumn
    0.53
    WillAppear
    0.52
     EconPapers
    0.51
    Activations Density 0.117%

    No Known Activations