© 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. 19-GEMMASCOPE-RES-16K
    11. 3473
    Prev
    Next
    INDEX
    Explanations

    the presence of relational and procedural phrases pertaining to structural descriptions and functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     sû
    -0.62
    livé
    -0.58
    ViewImports
    -0.56
    JNIEnv
    -0.56
    mybatisplus
    -0.56
     innebär
    -0.55
    ولی
    -0.55
     mē
    -0.54
     letzt
    -0.53
    !("{
    -0.53
    POSITIVE LOGITS
     replaced
    0.64
     removed
    0.58
     intact
    0.58
     OMITTED
    0.56
     changed
    0.55
     separate
    0.54
    expandindo
    0.52
     himo
    0.51
     omitted
    0.51
     absent
    0.51
    Activations Density 0.859%

    No Known Activations