© 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. 73
    Prev
    Next
    INDEX
    Explanations

    references to original content or works

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

    Text containing the word "original"

    np_acts-logits-general · gemini-2.0-flash

    original phrases

    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
    StructEnd
    -0.64
    PerformLayout
    -0.62
     âgées
    -0.61
    webElementXpaths
    -0.60
     vPvB
    -0.59
    rawDesc
    -0.59
    verwijspagina
    -0.59
    chaun
    -0.59
    ValueStyle
    -0.58
    MethodManager
    -0.57
    POSITIVE LOGITS
     Original
    0.81
    Original
    0.79
     ORIGINAL
    0.74
    原
    0.72
    ORIGINAL
    0.72
     orig
    0.70
     originals
    0.70
    splan
    0.67
     source
    0.66
     inal
    0.64
    Activations Density 0.076%

    No Known Activations