© 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. 10017
    Prev
    Next
    INDEX
    Explanations

    mentions of monetary payments or financial transactions

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

    Text after specific punctuation or bracketed terms

    np_acts-logits-general · gemini-2.0-flash

    legal texts and technical terms

    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
     Himself
    -0.59
     Buen
    -0.57
    addCriterion
    -0.55
    ρον
    -0.55
    getMy
    -0.55
    Fot
    -0.55
     Chrif
    -0.55
     consciences
    -0.54
    ándome
    -0.53
     pascal
    -0.53
    POSITIVE LOGITS
    ValueStyle
    0.83
    PageRoute
    0.65
     kehadiran
    0.61
    MessageOf
    0.61
    BagLayout
    0.60
    ReusableCell
    0.59
     EconPapers
    0.59
     beginnetje
    0.59
     him
    0.58
    TestingModule
    0.58
    Activations Density 0.253%

    No Known Activations