© 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. 22-GEMMASCOPE-RES-16K
    11. 3913
    Prev
    Next
    INDEX
    Explanations

    repeated patterns of numbers and characters that resemble coding or scripting language syntax

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

    Part of software file paths or ORCIDs

    np_acts-logits-general · gemini-2.0-flash

    chemical formulas and identifiers

    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
    AntiForgeryToken
    -0.74
    BagLayout
    -0.59
     chal
    -0.56
    requireNonNull
    -0.51
    GenerationType
    -0.48
    wound
    -0.48
     wound
    -0.48
     Himo
    -0.47
    lix
    -0.47
     ProtoMessage
    -0.47
    POSITIVE LOGITS
    MigrationBuilder
    0.87
    хьтан
    0.64
     gæ
    0.57
     onBind
    0.57
     createSprite
    0.56
    protoimpl
    0.55
     Италијани
    0.54
     ExecuteAsync
    0.53
     piłkarz
    0.51
    GEBURTSDATUM
    0.51
    Activations Density 0.449%

    No Known Activations