© 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. 1259
    Prev
    Next
    INDEX
    Explanations

    phrases indicating frequency of occurrences or repetitions

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

    Number of occurrences: "times"

    np_acts-logits-general · gemini-2.0-flash

    quantifying frequency with times

    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
    UnusedPrivate
    -0.77
    AllowUser
    -0.69
     intptr
    -0.66
    migrationBuilder
    -0.64
    ⓧ
    -0.63
     sumpay
    -0.61
    MongoClient
    -0.58
    Và
    -0.56
     caterpillars
    -0.56
     MongoClient
    -0.55
    POSITIVE LOGITS
     layui
    0.61
     lipat
    0.60
     jährlich
    0.59
    Viitteet
    0.58
     CascadeType
    0.58
    Демографія
    0.57
     للمعارف
    0.56
     magnification
    0.55
    yearly
    0.53
     seguida
    0.52
    Activations Density 0.155%

    No Known Activations