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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 12356
    Prev
    Next
    INDEX
    Explanations

    elements related to searching or finding something significant

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

    "Find" or "finding" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    finding something

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebVitals
    -0.74
    ViewFeatures
    -0.61
    migrationBuilder
    -0.61
    ftagPool
    -0.59
     IMDG
    -0.58
     Numerade
    -0.57
    /*
    -0.57
    dbo
    -0.57
    ℗
    -0.57
     AFFAIRS
    -0.56
    POSITIVE LOGITS
     ways
    1.00
     Finding
    0.86
    Finding
    0.76
    find
    0.74
     suitable
    0.74
     finne
    0.73
     find
    0.73
     Find
    0.72
    suitable
    0.69
     solace
    0.68
    Activations Density 0.197%

    No Known Activations