© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 13662
    Prev
    Next
    INDEX
    Explanations

    programming-related comments and documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    PHP code or code-related terms

    np_acts-logits-general · gemini-2.0-flash

    born out of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UserScript
    -0.67
    sizeCache
    -0.65
    WriteAttribute
    -0.61
    MigrationBuilder
    -0.60
     елның
    -0.59
    antMatchers
    -0.57
     GenerationType
    -0.57
    onViewCreated
    -0.56
    PostInfinity
    -0.56
    readAs
    -0.54
    POSITIVE LOGITS
    class
    0.97
    use
    0.92
    namespace
    0.80
    Class
    0.74
     class
    0.73
    include
    0.67
    require
    0.66
     use
    0.65
     Class
    0.63
    defined
    0.63
    Activations Density 0.049%

    No Known Activations