© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 20-GEMMASCOPE-RES-16K
    11. 16300
    Prev
    Next
    INDEX
    Explanations

    coordinating conjunctions and conjunctions expressing contrast or addition

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

    Sentences starting with conjunctions

    np_acts-logits-general · gemini-2.0-flash

    and but conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -1.38
    MigrationBuilder
    -1.28
    Personendaten
    -1.25
    SequentialGroup
    -1.21
    aarrggbb
    -1.16
    uxxxx
    -1.14
    TagMode
    -1.13
     ivelany
    -1.12
    WireFormatLite
    -1.12
    XmlAccessType
    -1.11
    POSITIVE LOGITS
    ,
    0.84
    !
    0.69
    es
    0.59
    oner
    0.57
    -
    0.56
    to
    0.54
    ie
    0.54
    os
    0.54
    n
    0.53
    ant
    0.51
    Activations Density 0.153%

    No Known Activations