© 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. 11751
    Prev
    Next
    INDEX
    Explanations

    percentages and numerical representations

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

    Followed by numbers, especially in code or links

    np_acts-logits-general · gemini-2.0-flash

    programming syntax and placeholders

    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
    KURZBESCHREIBUNG
    -0.84
    ItemBackground
    -0.79
    StructEnd
    -0.79
    contentLoaded
    -0.77
     betweenstory
    -0.76
    mergeFrom
    -0.76
    AsUp
    -0.72
    complexContent
    -0.72
    adpleegd
    -0.71
    principalTable
    -0.70
    POSITIVE LOGITS
    tagHelper
    0.60
     iParam
    0.59
     localObject
    0.53
    TagHelpers
    0.50
    iParam
    0.50
    arg
    0.50
    éndolo
    0.49
     uParam
    0.48
     Mand
    0.47
     وتسجيلات
    0.47
    Activations Density 0.090%

    No Known Activations