© 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. 13269
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names mentioned in the text

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

    Followed by a quotation

    np_acts-logits-general · gemini-2.0-flash

    names saying statements

    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
    MigrationBuilder
    -0.76
     EconPapers
    -0.71
    verwijspagina
    -0.69
     AssemblyCulture
    -0.66
    '};
    -0.63
    ())));
    -0.61
     nahilalakip
    -0.61
    >())
    -0.60
    GOTREF
    -0.60
     '\\;'
    -0.60
    POSITIVE LOGITS
     referring
    1.02
     refiri
    0.96
     adding
    0.79
     referencing
    0.77
     ajout
    0.69
     summing
    0.69
     quoting
    0.69
     recalling
    0.68
     sambil
    0.68
     describing
    0.68
    Activations Density 0.080%

    No Known Activations