© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 13120
    Prev
    Next
    INDEX
    Explanations

    different data types and their manipulation in programming

    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
    TestTools
    -0.57
     SDLK
    -0.55
    ↵↵
    -0.52
     mergeFrom
    -0.52
    sidemargin
    -0.52
    msgTypes
    -0.50
     eventdata
    -0.49
    ész
    -0.49
    ><!--
    -0.47
    %;
    -0.47
    POSITIVE LOGITS
    label
    0.89
    LABEL
    0.88
     label
    0.78
    Label
    0.74
     Label
    0.72
     LABEL
    0.68
     labelling
    0.67
     labeled
    0.66
    Labeled
    0.66
     labeling
    0.63
    Activations Density 0.049%

    No Known Activations