© 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. 11558
    Prev
    Next
    INDEX
    Explanations

    discussions about judgment and decision-making

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

    "it" followed by a conditional word

    np_acts-logits-general · gemini-2.0-flash

    whether it

    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
    WireFormatLite
    -0.53
     ModelExpression
    -0.52
    TableAdapter
    -0.51
    >{@
    -0.49
    thday
    -0.49
    addValue
    -0.49
    BeginContext
    -0.48
     وتسجيلات
    -0.47
    ertor
    -0.47
    δά
    -0.46
    POSITIVE LOGITS
     it
    1.62
    It
    1.20
     It
    1.17
    it
    1.03
    それは
    0.80
     Đó
    0.72
     było
    0.68
     trataba
    0.68
     آن
    0.67
     būtų
    0.67
    Activations Density 0.193%

    No Known Activations