© 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. 3872
    Prev
    Next
    INDEX
    Explanations

    references to functions and operations in programming or mathematical contexts

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

    Followed by "ants", "ational", or similar suffixes

    np_acts-logits-general · gemini-2.0-flash

    approximants

    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
    migrationBuilder
    -0.65
     AssemblyCulture
    -0.63
    jalá
    -0.62
    setVerticalGroup
    -0.62
    ViewFeatures
    -0.61
    хьтан
    -0.61
    RuleContext
    -0.60
    :✨
    -0.59
    antaranya
    -0.59
     Италијани
    -0.58
    POSITIVE LOGITS
    nadequate
    0.46
    toHave
    0.43
    ational
    0.42
    VYMaps
    0.42
    ectious
    0.41
    vastatin
    0.41
    ↩
    0.41
    addComponent
    0.40
    InitStructure
    0.40
     gi
    0.40
    Activations Density 0.220%

    No Known Activations