© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 13501
    Prev
    Next
    INDEX
    Explanations

    functions and operations related to loading, saving, and processing data in programming contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    ArgsConstructor
    -0.74
    VersionUID
    -0.73
     nakalista
    -0.70
    #![
    -0.66
     Audiodateien
    -0.65
     يتيمه
    -0.63
     LoggerFactory
    -0.62
    AnimationsModule
    -0.62
    ValueStyle
    -0.58
    SerializedName
    -0.56
    POSITIVE LOGITS
    all
    0.71
    Single
    0.62
    单个
    0.62
    ALL
    0.61
    Existing
    0.61
     all
    0.60
    AndUpdate
    0.60
    Entire
    0.60
    AndSet
    0.59
     entire
    0.58
    Activations Density 0.371%

    No Known Activations