© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15012
    Prev
    Next
    INDEX
    Explanations

    time-related references and expressions

    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
    AutoField
    -0.60
    CppCodeGen
    -0.59
    aarrggbb
    -0.56
    endphp
    -0.56
    )?;
    -0.56
    '])){
    -0.55
    &&\
    -0.52
    ArrowToggle
    -0.52
    URIComponent
    -0.52
    queryInterface
    -0.51
    POSITIVE LOGITS
     Edited
    0.80
     Thread
    0.79
     edited
    0.79
     thread
    0.76
    FTFY
    0.75
     forum
    0.75
     QUOTE
    0.74
     Forum
    0.73
    findpost
    0.73
    帖最后由
    0.73
    Activations Density 0.289%

    No Known Activations