© 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. 20-GEMMASCOPE-RES-16K
    11. 14945
    Prev
    Next
    INDEX
    Explanations

    terms related to controversy and its implications in various contexts

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

    preceding/related to locations, areas, or boundaries

    np_acts-logits-general · gemini-2.0-flash

    around or surrounding

    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
    getSeconds
    -0.54
    GEBURTSDATUM
    -0.54
     continúas
    -0.53
     AssemblyCulture
    -0.51
    Jereo
    -0.51
     nonatomic
    -0.50
     TextInputType
    -0.48
    politico
    -0.48
     مرئيه
    -0.47
     ujednoznacz
    -0.47
    POSITIVE LOGITS
     around
    2.62
     surrounding
    2.43
    around
    2.31
     Around
    2.30
    Around
    2.26
     AROUND
    2.23
     surrounds
    2.21
     autour
    2.21
     surround
    2.05
     intorno
    2.03
    Activations Density 0.466%

    No Known Activations