© 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. 9068
    Prev
    Next
    INDEX
    Explanations

    themes related to relationships and representations of marriage

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

    symbols and representation

    np_acts-logits-general · gemini-2.0-flash

    symbolize or represent

    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
     Roskov
    -0.85
    setVerticalGroup
    -0.72
    TagMode
    -0.71
    enumi
    -0.71
    ագրություններ
    -0.70
    InjectAttribute
    -0.70
     Italijanski
    -0.66
    expandindo
    -0.64
     Exactos
    -0.63
    SourceChecksum
    -0.63
    POSITIVE LOGITS
     symbolize
    2.02
     symbolizes
    1.98
     symbo
    1.96
     symbol
    1.89
     represent
    1.88
     representing
    1.87
     simbo
    1.85
     represents
    1.81
     symbolism
    1.73
     symboli
    1.72
    Activations Density 0.349%

    No Known Activations