© 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. 9985
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations used in equations

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

    Mathematical and code snippets

    np_acts-logits-general · gemini-2.0-flash

    mathematical expressions and code snippets

    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
     more
    -0.50
    ,
    -0.47
    卉
    -0.47
    :
    -0.47
     Bel
    -0.46
     Li
    -0.45
     Tait
    -0.44
     li
    -0.44
    Tbl
    -0.43
     and
    -0.43
    POSITIVE LOGITS
    DockStyle
    1.20
    setVerticalGroup
    1.13
    awtextra
    1.08
     disambiguazione
    1.07
    ]=>
    1.05
    EndGlobalSection
    1.03
    memoized
    1.03
    InjectAttribute
    1.00
    PerformLayout
    0.97
     GenerationType
    0.95
    Activations Density 0.445%

    No Known Activations