© 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. 14919
    Prev
    Next
    INDEX
    Explanations

    continuous markers or reoccurring items in structured data

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

    Dates with day, month, and year

    np_acts-logits-general · gemini-2.0-flash

    dates and numbers

    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
     protoimpl
    -0.75
    sizeCache
    -0.68
    SourceChecksum
    -0.67
    +#+
    -0.65
     &___
    -0.63
    PostExecute
    -0.61
    styleType
    -0.61
    EndInit
    -0.60
    fjspx
    -0.60
     crossorigin
    -0.60
    POSITIVE LOGITS
    mità
    0.54
    الية
    0.53
     tenham
    0.50
    mige
    0.48
    關於
    0.48
    popd
    0.48
     Clarion
    0.47
    关于
    0.47
    getItem
    0.47
     pro
    0.47
    Activations Density 0.046%

    No Known Activations