© 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. 18-GEMMASCOPE-RES-16K
    11. 2131
    Prev
    Next
    INDEX
    Explanations

    references to time periods and historical contexts

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

    Follows a number

    np_acts-logits-general · gemini-2.0-flash

    reporting on events and categories

    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
    TypedDataSet
    -0.75
    MigrationBuilder
    -0.68
     Meksiku
    -0.68
     незавершена
    -0.66
     réflex
    -0.66
    ScopeManager
    -0.66
     arabic
    -0.64
     चीज़ों
    -0.63
    webElementXpaths
    -0.63
     tartalomajánló
    -0.61
    POSITIVE LOGITS
     reportedly
    0.76
     debut
    0.66
     announced
    0.65
     defence
    0.61
     unbeaten
    0.59
     led
    0.59
     inaugural
    0.58
     defeated
    0.57
     alleged
    0.57
     said
    0.57
    Activations Density 1.244%

    No Known Activations